LLM Safety Evaluation

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

16 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 177

Oct 5, 2026cs.LG

Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints

We evaluate large language models (LLMs) in multi-turn interactions through their time-to-event: the number of interaction steps required to produce an event of interest, such as a successful jailbreak or agentic task completion. Under limited compute, interactions may be terminated before the event occurs, so that event times are only partially observed (censored). Existing allocation methods for calibrating time-to-event bounds satisfy the budget only in expectation and can exceed the available budget on a particular evaluation run. Enforcing a hard constraint is particularly challenging as the cost of a trajectory is initially unknown. We introduce Hard-budget Allocation with Reflow for Predictive calibration (HARP), a budget allocation that satisfies hard resource constraints and adaptively reallocates unused budget. We show how to use HARP to construct lower predictive bounds (LPBs) on the time-to-event and to estimate evaluation metrics such as the jailbreak rate on a fixed benchmark. Although HARP induces dependence in acquisition decisions across different trajectories, we prove that HARP never exceeds the target budget, that its LPBs have finite-sample coverage guarantees, and that its metric estimates are unbiased. Experiments on agentic task success, LLM jailbreaks, toxic content generation, and RAG hallucinations show that HARP achieves coverage close to the nominal level with low variance, while never exceeding the given budget.

Shai Feldman, Yaniv Romano

Department of Computer Science, Technion IIT, Israel · Department of Electrical and Computer Engineering, Technion IIT, Israel

LLM Evaluation LLM Safety Evaluation

Sep 30, 2026cs.CR

Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners

Embodied vision-language models (VLMs) are increasingly deployed as high-level planners for robots because they generalize across diverse environments. However, this requires their safety alignment to also hold in unseen environments. Existing red-teaming assumes an adversary who optimizes the prompt, the pixels, or text in the environment, and existing benchmarks ask whether a planner recognizes or mitigates a hazard in a fixed scene. Neither asks whether a refusal the planner has already given survives an ordinary change to the environment. We ask that question by placing a single everyday object into the environment, with no pixel, gradient, or prompt under adversarial control. On

846

tasks that a constitution-guarded planner initially refuses, we find

20.2\%

of tasks can be flipped to compliance by one or more objects, and the number of objects differs from one task to another. In addition, the object need not be chosen for the task, i.e., items drawn from a fixed list, with no knowledge of the environment or the instruction, bypass safety about as often as items proposed for the specific task. We qualitatively contrast the tasks bypassed most and least often and find that the distinction lies in how conspicuous the hazard is in the instruction and environment. Susceptibility to safety bypass is therefore a property of the task, which we call its \emph{malleability}, and we show that it can be predicted before the target is ever queried. A composite of signals read from a small open-source VLM identifies malleable tasks

2.4\times

as often as picking at random. Everyday objects, whether placed by an adversary or introduced by ordinary rearrangement of the environment, are thus sufficient to overturn a refusal. Because susceptibility is determined by how a task is specified, we recommend assessing malleability per task prior to deployment.

Leo Y. Lin, Mikhail Kuznetsov, Muslum Ozgur Ozmen +1

Purdue University · Amazon · Arizona State University

Robot Safety LLM Safety Evaluation VLMs for Robotics Robustness of VLA Models

Sep 29, 2026cs.CR

Evaluating Whether GPT-6 Astra Performs Unsanctioned Supply-Chain Attacks

This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions outside the scope of their assigned task. We evaluate whether frontier models conduct supply-chain attacks against out-of-scope, third-party targets when placed in difficult cybersecurity challenges, motivated by recently observed cases of models attacking real open-source repositories during evaluations. Applying our methods to GPT-6 Astra and previous OpenAI models, with cyber safeguards disabled, we find that GPT-6 Astra attempts complete supply-chain attacks in simulation at a higher rate than GPT-5.6 Sol and GPT-5.5. This includes writing malicious code as a contribution to an out-of-scope open-source codebase, creating fake identities to deceive open-source developers, and submitting benign contributions before malicious ones. GPT-6 Astra frequently reasons about the scope of the challenge in its chain-of-thought yet still proceeds to attack out-of-scope targets; it often asks for permission, and treats an automated message as as authorisation; and it continues to take unsanctioned actions, at a reduced rate, when internet access is more explicitly disallowed. Our evaluation builds on an internal version of Petri, an open-source LLM auditing tool, with all tool calls simulated by other LLMs, so that no real network access, systems or third-party repositories are reachable and no real-world harm is caused. Finally, we discuss limitations, in particular simulation awareness. We believe simulation awareness may have driven some of the observed behaviour but does not remove our concern. Our results suggest that defences beyond model alignment, such as sandboxing and monitoring, are increasingly critical for safe and secure deployment.

Alexandra Souly, Kai Fronsdal, Abby D'Cruz +2

UK AI Security Institute · UK AISI Research Affiliate

LLM Auditing AI Agent Security Software Supply Chain Security LLM Safety Evaluation

Sep 28, 2026cs.AI

Jailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool Agents

As large language models increasingly operate as tool-using agents, post-jailbreak safety feedback is often assumed to serve as a reliable safeguard; however, how lingering jailbreak context shapes subsequent agent behavior remains largely unexplored. To systematically examine this dynamic, we introduce a paired continuation framework across 192 parent tasks spanning 42 domains, evaluating 12,148 analyzed continuation pairs (curated from a 12,288-pair initially design) across eight diverse agents. We find that identical safety feedback induces sharply model-dependent behavioral routing rather than uniform protection: redirecting unsafe trajectories toward legitimate completion (\emph{rescue}), sustaining unauthorized execution (\emph{persistent unsafe}), or triggering over-refusal on benign tasks (\emph{collateral loss}). Through layer-wise activation patching, we discover a shared \emph{late-commit pattern} where causal intervention effects surge sharply near the final layers (relative depths of 0.958--0.984) despite an over 30-fold variation in peak magnitude across architectures. Crucially, critical-layer representations correlate with macroscopic routing outcomes, and intervening at these layers causally alters concrete next-step tool actions. Building on this causal foundation, we test whether localized intervention-derived features can serve as predictive proxies for full-trajectory routing outcomes on unseen parent tasks under leave-one-parent-task-out evaluation, finding that they provide viable predictive signals in responsive agents with peak ROC AUCs reaching 0.675 for \emph{rescue}, 0.777 for \emph{collateral loss}, and 0.702 for \emph{persistent unsafe}. These findings establish a mechanistic lens and a predictive baseline for anticipating the safety and utility trade-offs of post-jailbreak feedback in autonomous agents.

Xi Wang, Songlei Jian, Yiming Zhang +5

National University of Defense Technology

LLM Safety Evaluation Causal Interventions in Language Models LLM Agent Safety

Sep 24, 2026cs.CL

ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts

ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate detection in Arabic memes, while Track B addresses harmful prompt detection for Arabic LLM safety evaluation. In total, 58 teams registered, 35 participated in the final evaluation, and 27 submitted system-description papers. Participating teams explored models such as AraBERT, Jais, and Qwen3-VL. The best systems achieved macro-F1 scores of 0.823 on A1, 0.419 on A2, 0.984 on B1, and 0.790 on B2. Fine-grained meme classification in A2 was the most challenging setting, partly due to sparse labels and train-test distribution shifts.

Firoj Alam, Md. Rafiul Biswas, Mohamed Bayan Kmainasi +5

Qatar Computing Research Institute, Qatar · Hamad Bin Khalifa University, Qatar · APAVI.AI, France +1

LLM Safety Benchmarks Arabic NLP Language Model Safety Evaluation Hate Speech Detection LLM Safety Evaluation

Sep 17, 2026cs.AI

From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization

Large language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-language requests to vehicle functions creates a safety-critical authorization problem. Before executing a command, the system must choose whether to execute, refuse, clarify, require confirmation, defer to manual control, trigger an emergency response, or make no tool call. To our knowledge, prior evaluations do not isolate this pre-action decision across speaker role, authentication status, vehicle state, and tool availability. We introduce a 202-scenario benchmark with Reference Decisions under a seven-class taxonomy. We evaluate two local open-weight models and three API-based LLMs using Decision Alignment and safety-specific error metrics. Alignment ranges from 40.1% for Llama 3.2 3B to 89.1% for Gemini 3.1 Pro Preview. The API-based models score between 83.2% and 89.1%, with no statistically significant differences among them. Even these models produce two to three False Executes among 161 non-execution scenarios, and persistent errors remain in confirmation and manual-control decisions. A controlled Llama 3.2 3B ablation increases alignment to 40.1% under the structured authorization policy, versus 28.2-29.2% under schema-only and generic-safety baselines, but it does not eliminate False Executes. Structured LLM decisions are therefore insufficient as a standalone safety mechanism, and deployment requires an independent enforcement layer that verifies tool permissions and vehicle-state constraints before invoking any vehicle function.

Diba Afroze, Xingli Zhang, Yazhou Tu +1

University of Louisiana at Lafayette, Lafayette, LA 70503, USA · Auburn University, Auburn, AL 36849, USA

LLM Safety Benchmarks LLM Safety Evaluation Conversational Agents Tool Access Control for LLM Agents

Sep 15, 2026cs.AI

Do Frontier Models Seek Safety Evidence Before Acting?

Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting. We introduce SAFE, a controlled benchmark in which models make deployment decisions with optional evidence that varies in retrieval cost, probability, severity, and presentation. Across GPT-5.5, o3, Claude Opus 4.8, and Claude Sonnet 4.6, we find distinct evidence-acquisition policies: Opus inspects nearly by default, o3 is the most skip-heavy and threshold-sensitive, and GPT-5.5 and Sonnet occupy intermediate regimes. Inspection increases strongly with severity and decreases with retrieval cost, whereas probability has much weaker behavioral influence: increasing the stated likelihood of a problem from 10% to 70% changes inspection by at most 21 percentage points. Despite these differences, Stage 1 rationales are dominated by expected-value reasoning across models. A cost-obligation decomposition further shows that avoidance is driven primarily by retrieval friction and explicit threats to the deployment payoff rather than by the remediation duties created by knowing. Counterfactual interventions reveal a further mismatch between behavior and explanation: evidence framing can strongly change decisions near the inspection boundary while going largely unmentioned, whereas probability is frequently cited despite having little causal influence. These results suggest that deployment-time safety depends not only on how models respond to known risks, but also on whether they acquire the evidence needed to know that acting is safe.

Omer Tafveez

University of Michigan

LLM Safety Benchmarks LLM Safety Evaluation Decision-Making under Uncertainty

Sep 15, 2026cs.CL

Benchmarking Factual Robustness of LLMs via Multi-conversation Persuasion

As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against \textit{persuasion attacks}---attempts to inject misinformation or enforce counterfactuals---has become a critical safety concern. Existing red-teaming frameworks typically evaluate models in multi-turn dialogues where the target model retains full conversation history. We identify a critical flaw in this setting termed \textbf{

Refusal Inertia''}: a model's initial refusal often propagates through subsequent turns largely to maintain contextual consistency, thereby masking its true vulnerability to sophisticated, isolated persuasion attempts. To rigorously evaluate the

cold-start'' defense capabilities of SOTA models, we introduce the \textbf{SAST-IR} (Stateful Attacker, Stateless Target - Iterative Refinement) framework. By enforcing a memory wipe on the target while retaining the attacker's history, we simulate a worst-case adversarial setting using \textbf{multi-turn} (stateless) iterations. Leveraging \textbf{CP-Agent} (Cognitive Persuasion Agent), an enhanced diagnosis-guided agent, our experiments on the custom \textsc{CounterFact-Strict} dataset (

N=50

) yield alarming results: simple, diverse attack strategies achieved a staggering \textbf{96%} success rate, exposing severe brittleness in memory-less defense. Furthermore, we reveal a \textbf{``Complexity Paradox''}: while complex, iteratively refined attacks are effective, they often trigger defensive compliance, whereas simple strategies achieve a higher rate of genuine persuasion (\textbf{84.7%}). Our code and dataset are available at GitHub, https://github.com/cza1006/llm-persuasion-defense.

Zhuoang Cai

The Hong Kong University of Science and Technology

Adversarial Attacks on LLMs LLM Safety Evaluation Persuasion in Language Models Language Model Robustness

Sep 14, 2026cs.CR

Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs

Language model safety is typically evaluated one interaction at a time. We show that a weaker, unaligned model can split a harmful task into benign-looking subproblems, consult a stronger aligned model independently on each, and combine the answers locally. We call this attack capability laundering. Unlike a jailbreak, no single response is a harmful task. We measure consultation-aided uplift using tasks that a raw frontier model solves, the aligned frontier refuses, and the unassisted orchestrator fails. We evaluate GPT-5.5, Claude Opus 4.8, and Grok-4.3 as consultants to four local orchestrators on CyBench, BountyBench, and harmful CBRN requests. On CyBench, Gemma-4-31B recovers 8/14 candidates with GPT-5.5 and 7/9 with Opus, compared with 2/21 and 4/15 for Gemma-4-12B. On BountyBench, Gemma-4-31B recovers 3/9 and 2/3 candidates, while Muse-Glimmer-30B recovers none of 22 and 13. For CBRN, we measure uplift across eight steps of a hypothetical bioweapon attack chain and find that consultation raises Gemma-4-31B's mean rubric score from 62.3 to 83.1 on a 100-point rubric scale. These results expose a gap in current defenses: refusing a harmful task does not prevent frontier capabilities from being transferred and composed across many individually permitted interactions.

Mark Russinovich, Blake Bullwinkel, Giorgio Severi +2

Microsoft Azure · Microsoft

Adversarial Attacks on LLMs Cybersecurity LLM Safety Evaluation

Sep 11, 2026cs.LG

DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis

A structurally valid DeFi workflow can still authorize a costly trade. We introduce DeFiFlowBench, a benchmark of 207 team-authored prompts for natural-language DeFi workflow synthesis. It measures graph coverage, configuration completeness, and declared safety predicates, then tests supported trade configurations on a local EVM. Direct, constrained, and few-shot prompting produce 14-19 unsafe held-out executions per configuration under a fixed 5% price-impact cap. A slippage bound derived from a quote does not prevent the price impact of the order itself. We propose Koan-Safe, which combines a prompt-only intent parser, a replaceable generator, and structural repair with default safety parameters. On 75 held-out workflow prompts, its hybrid variant scores 0.67 on the static safety proxy, compared with 0.33 for the best baseline. Koan-Safe records no unsafe executions on the saved benchmark outputs. A matched-candidate ablation produces 14-17 unsafe executions when enforcement is disabled. Additional tests expose the limits of default injection: permissive existing thresholds can still authorize unsafe trades. A separately evaluated policy cap addresses this failure on a 36-case diagnostic grid. These results support explicit trade protections and execution-based evaluation, while distinguishing declared safety from a general guarantee.

Abhinav Rajeev Kumar, Harshit Arora, Varun Singh +1

SRM Institute of Science and Technology

LLM Safety Benchmarks LLM Guardrails Decentralized Finance LLM Safety Evaluation

Sep 9, 2026cs.CR

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically evalu- ate guardrails for code generation security. It covers 1) text-to-code generation with 1000 high-quality malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) that embeds malicious intent in a legitimate fictional software-development sce- nario; and 2) code-to-code generation with 331 code prompts spanning code infilling, code completion, and code translation. We empiri- cally evaluate 9 guardrails across seven LLMs. We find that current guardrails perform poorly against malicious code-generation re- quests: for text-to-code, the average attack success rate (ASR) after jailbreaks reaches about 50% for many guardrails; for code-to- code, average ASR approaches 100% on base LLMs and remains high across many guardrails (14.4% to nearly 100%). Our FSA also achieves ASR close to 100% across many guardrails, raising major reliability concerns for real-world software development. To sup- port future research, CS-Guard uses a modular three-layer guardrail taxonomy that lets devel- opers register guardrails for evaluation. We release the benchmark and data to enable fur- ther community evaluation.

Jinyang Li, Mingyu Guo, Hung X. Nguyen

Adelaide University Adelaide, Australia

LLM Guardrails Adversarial Attacks on LLMs Safety Filtering LLM Safety Evaluation Secure Code Generation

Sep 9, 2026cs.RO

CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making

Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-by-step reasoning, creating opportunities for sophisticated autonomous robots. However, recent research reveals that reasoning models verbalize their actual decision processes only 25-39% of the time, with faithfulness degrading 44% on complex tasks. This paper presents CT-SAFR (Chain-of-Thought Safety and Faithfulness for Robotics), a multi-layered verification framework achieving 94.2% hallucination detection (n = 500, 95% CI: 91.8-95.9%) with sub-500ms latency. Through a warehouse robot case study, this work demonstrates 87% reduction in unsafe reasoning outputs (p < 0.001) and provides recommendations for responsible deployment of reasoning-capable autonomous robots.

Cagri Temel

Hezarfen LLC Seattle, WA, USA · Grand Canyon University Phoenix, AZ, USA

CoT Faithfulness Large Language Model-Based Robot Planning Robot Safety LLM Hallucination Detection LLM Safety Evaluation

Sep 8, 2026cs.CL

Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning

Aligned language models fail under two independent pressures: the structural jailbreak class recently formalized as Involuntary In-Context Learning (IICL), which reframes a harmful request as the final missing cell of a data-labeling task completed by pattern rather than judged as content; and the erosion of safety alignment outside English. A natural hypothesis is that these compound. We test it directly. Using a deterministic IICL operator and a StrongREJECT-style rubric judge, we red-team two Google Gemini models on two benchmarks, a 30 general-harm behaviours from HarmBench and 30 financial-abuse behaviours from FinProof, each under a single-shot baseline and under IICL in four languages (English, Spanish, Hindi, Arabic). First, IICL generalizes to a second provider and is worse in finance: it lifts attack success from <=6.7% to 80-90% on HarmBench and 97-100% on FinProof, an order of magnitude above the <=24% its introducing study reported on OpenAI's GPT-5.4. Second, against the hypothesis, forcing the IICL output into a non-English language does not stack the two weaknesses, it attenuates the attack. Eleven of twelve non-English conditions score below their English baseline (sign test, p~0.003), the lone exception a ceiling tie near 100%; on the stronger model's financial set Arabic collapses from 100% to 33%. We attribute this to a relevance curse: once structure has unlocked compliance, the models produce lower-quality harmful content in lower-resource languages, which a substance-grading judge scores as partial. The pattern replicates under an independent non-Google judge (Cohen's kappa=0.86, 377 paired verdicts), and 76.6% of non-English responses were verified in-language. Jailbreak vulnerabilities are therefore not additive; the dominant residual risk is the English structural attack, most acute for financial abuse, not a multilingual one.

Tejasvi C. Addagada

Independent researcher

LLM Safety Benchmarks Multilingual Language Model Evaluation Adversarial Attacks on LLMs LLM Safety Evaluation

Sep 7, 2026cs.CV

SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMs

Multimodal Large Language Models (MLLMs) show strong progress on vision-language tasks, yet their reliability in safety-critical settings remains underexplored. Fire-smoke understanding is central to public safety and disaster response, but most existing benchmarks lack diverse real-world scenarios and context-aware evaluation. We introduce SAFIRE, a large-scale benchmark for fire-smoke understanding in MLLMs, comprising 83K captioned images from 20 scenarios and 193K multiple-choice VQA (MCVQA) generated from a 9.7K-image subset, spanning 10 evaluation dimensions from basic perception to higher-order reasoning. A GPT-5.4-assisted multi-stage verification pipeline with MLLM majority voting ensures annotation quality. Evaluating ten open-source MLLMs (8B-38B) yields an average accuracy of 61.9%, exposing major gaps in safety-critical reasoning. We further show that adapting vision encoders with only 7% of our domain-specific data boosts fire-scene classification accuracy from 20.1% to 64.5%, indicating that carefully curated data can yield substantial gains even when data volume is limited. All datasets, models, and code are available at https://risys-lab.github.io/SAFIRE/.

Pengfei Li, Naufal Suryanto, Sicheng Zhang +2

Khalifa University · University of Western Australia

LLM Safety Benchmarks LLM Safety Evaluation Multimodal Model Evaluation

Sep 7, 2026cs.CL

Probing the Structure and Dynamics of LLM Value Expression through Value Conflicts

Ethical evaluation of Large Language Models (LLMs) often characterizes model values as static and monolithic. In contrast, we argue that LLM value expression is better understood as a structured yet dynamic phenomenon. To investigate this, we introduce Conflict-driven Value Probing, a controlled framework that places LLMs in value conflicts and implements four types of interventions that perturb these conflicts to probe LLM value expression. Applying this framework to ten LLMs, we identify three recurring patterns. (1) Expression duality: models shift from broad idealistic orientations in abstract assessment toward more pragmatic priorities in concrete conflicts. (2) Functional steerability: models readily reconfigure their expressed value profiles toward task-defined value objectives. (3) Bounded plasticity: such reconfiguration is not without constraints, i.e. pressure induces a security- and goal-oriented priority shift while negative framing distinguishes protected values from those more amenable to redirection. Together, these findings characterize both the structure and dynamics of LLM value expression: context flexibly reconfigures expressed priorities, yet within behavioral boundaries. This behavioral account provides a foundation for understanding controllability, alignment, and safety in LLMs. Code and data are available at https://github.com/ZeroGen-Lab/CFProbe.

Kaicheng Zhang, Jingyi Xiao, Renjun Hu +3

East China Normal University Shanghai, China

LLM Alignment LLM Safety Evaluation

Sep 7, 2026cs.RO

How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration

Large Language Models (LLMs) are increasingly employed to orchestrate robot behavior through natural-language interfaces, yet no benchmark exists to evaluate their reliability as safety-aware decision makers in human-humanoid collaboration. Unlike deterministic safety systems that enforce binary allow/deny decisions, LLM-based orchestrators exhibit a compliance spectrum ranging from overcompliance (refusing safe actions) to full safety violations. This paper introduces the first safety benchmarking environment for LLM orchestrators in human-humanoid collaboration, built on a Model Context Protocol (MCP)-based architecture with safety invariants grounded in ISO 10218-2:2025 protective measures. The benchmark defines five testable safety invariants, a four-level compliance taxonomy (correct compliance, overcompliance, undercompliance, full violation), and a three-layer evaluation pipeline (text prompting, simulated sensor-actuator loops, and physical validation on a Unitree G1 EDU humanoid). We report Layer-1 results: three cloud backends (Claude Haiku 4.5, GPT-4o-mini, Gemini 2.5 Flash) and a local open-weights baseline (qwen3:8b) across 40 100-turn sessions under full-context and sliding-window budget conditions, while the simulation and physical layers remain ongoing. We find that (1) model family determines the safety floor, as Claude and Gemini remain at or near zero violations while GPT-4o-mini commits up to 13 per session, (2) context management dissociates two failure axes, reducing mean behavioral issues by 42-57% for every cloud backend while nearly doubling GPT-4o-mini's violations (3.8 to 7.2 per session), and (3) proportional compliance, clamping movement speed to the rule-specified maximum rather than refusing, emerges consistently only in Gemini; the preliminary simulation layer reproduces the model ranking and the GPT-4o-mini failure-mode inversion.

Aulon Bajrami, Mohamed Elshamouty, Werner Kraus

Fraunhofer IPA Stuttgart, Germany

Robot Safety Human-Robot Collaboration LLM Safety Evaluation AI Agent Safety Benchmarks LLM Agent Safety

Sep 7, 2026cs.LG

The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability

Several properties safety monitors are asked to certify, among them cross-tenant noninterference, sandbagging and evaluation awareness, are 2-safety hyperproperties, witnessed only by two executions. The standard consequence is a binary impossibility: one trace cannot decide them. We replace the binary with a measurement. A tight bound puts the balanced accuracy of any single-trace monitor at

\tfrac12+\tfrac12\,TV(P_0,P_1)

, turning undecidability into a graded detectability frontier and defining an oversight gap: a monitor's shortfall below it. On a leak family with closed-form

TV

, nine LLM monitors are optimal at

TV=0

but capture little signal as

TV

grows; at

TV=1

, where a 20-line membership check scores

100\%

, they average

60.9\%

. That shortfall is mostly not capability: naming what to check closes

61\%

of it while leaving the

TV=0

control at chance. The same split runs through a

2{\times}2

factorial: an imagined second run leaves monitors at chance (

50.4\%

) while the same rule on an executed second run reaches

90.0\%

, and a stored oracle without a comparison procedure yields only

68.2\%

. Information and procedure are each necessary and neither is capability. Under nondeterminism, replay tracks a closed-form

k

-replay curve only under the right projection, and a projection frontier shows the resulting dilemma is forced: narrow misses

98.6\%

of off-channel leaks, broad flags

75.7\%

of clean traffic, and attainable accuracy decays like

1/(qm)

in the benign-variation rate and the channel count. Finally, two frontier LLM judges certified an earlier version of our own benchmark as sound while a sign test found a directional bias (

p=2.7\times10^{-5}

) that invalidated three of our findings. Construction validity for hyperproperty benchmarks should be proved mechanically, not audited by models.

Xin Xu

Carnegie Mellon University

LLM Safety Benchmarks LLM Safety Evaluation Language Model Auditing

Sep 3, 2026cs.AI

FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models

Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close to the ground truth can still violate operational constraints, combine fields in physically inconsistent ways, or fail to produce usable structured outputs. Existing evaluation protocols do not measure these failure modes reliably. We propose FLY-EVAL++, an evidence-driven evaluation protocol that combines deterministic verification of protocol compliance, physical feasibility, and safety constraints with fixed rubric-guided aggregation into interpretable multi-dimensional scores. We instantiate FLY-EVAL++ for Flight Trajectory and Attitude Prediction (FTAP) by extending the PilotBench setting with history-conditioned and multi-step prediction tasks. Across 66 LLMs, safety compliance is the most discriminative dimension of model behavior: models with comparable predictive performance differ by more than 28 points in safety score, and we observe recurrent failures including safety violations under physically plausible predictions and instability in multi-step rollouts. These results show that evaluation in safety-critical domains should measure constraint satisfaction and structured validity explicitly rather than rely on accuracy-centric reporting alone.

Yalun Wu, Junfeng Fang, Jiawei Wang +6

NExT++ Lab, School of Computing, National University of Singapore · 3Xiamen University · University of Manchester +4

LLM Safety Benchmarks LLM Safety Evaluation

Sep 2, 2026cs.CL

Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking

Multi-turn jailbreak attacks demonstrate that harmful intent can be distributed across dialogue, yet existing methods obscure what conversational mechanisms drive vulnerability. We introduce BLUEPRINT, a safety-evaluation framework separating a factorized social-influence strategy space from WORLDVIEWSIM, a cross-turn situational context module. Monte Carlo Tree Search optimizes turn-level combinations of 18 theory-grounded influence factors across a four-turn trajectory. Across six frontier models, BLUEPRINT achieves near-ceiling ASR on major open-weight and proprietary models, while requiring the fewest average queries (2.46). The resulting trajectories further reveal model-specific vulnerability among resistant targets: each responds to distinct influence factors and strategy transitions, yet all share a common recovery pathway-shifting toward concrete, executable task framing consistently escapes hard-refusal states. Ablations confirm operational cues matter most: making requests actionable has the largest impact, gain framing is unusually potent, and some legitimacy appeals can backfire. These findings suggest robust multi-turn safety requires monitoring not only harmful content, but also how dialogue state makes unsafe requests appear concrete and locally executable.

Siyu Chen, Haoran Wang, Xiaojian Li +3

1AI4S Center, Shanghai Qi Zhi Institute, Shanghai, 200232, China · College of AI, Tsinghua University, Beijing, 100083, China · 3Fangcun AI, Beijing, 100084, China +1

Multi-Turn Jailbreak Attacks LLM Safety Evaluation

Sep 2, 2026cs.AI

ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models

Safety alignment trains large language models to refuse harmful requests stated plainly, but that training is applied mostly to surface form. Requests that only recontextualise the same operational content, changing how the model reads it, are therefore only weakly covered. The ASCII Attack is one such recontextualisation. It is single-turn and black-box: one message, with no access to model internals. It embeds a fully legible harmful request in ASCIl-art characters, presents it as artwork, and asks for feedback. Unlike ArtPrompt, it hides nothing: the request stays readable. The reply is written as artistic critique and can contain operational detail that a plain request would have been refused for. Every framed prompt is paired with a direct-question control, so the contrast is isolated from topic, model and decoding variation. The contrast identifies a bundled surface, not one isolated channel. Across eleven models and eight harm topics, a harm-aware classifier judges 62% of framed prompts harmful against 42% of controls. On the most susceptible model the framed prompt succeeds 93% of the time. A single query matches or exceeds published single-query attacks under four of five harm judges. The effect tracks the model more than the topic and does not diminish with scale. At least one judge dissents from the panel majority on nearly two-thirds of framed rows, which is itself a measurement-validity finding. That pattern is consistent with mismatched generalisation.

Da Cheng Gu, Yifei Dong, Xinghao Yang +2

Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, 2007, Australia · China University of Petroleum, China · Shandong University, China

LLM Jailbreak Attacks LLM Safety Evaluation Adversarial Prompt Generation

Sep 1, 2026cs.CL

SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue

Large Language Models (LLMs) are increasingly used in advice seeking and decision making that may affect social judgements. Despite stigma's profound effects on people and communities, benchmarks remain scarce. Existing general-domain evaluations typically rely on static prompts and fixed-format tasks, overlooking conversational contexts and audience effects in everyday communication. To address these gaps, we introduce SDARE-Bench, the first scenario-based benchmark evaluating both stigma detection and open-ended response generation in LLMs, comprising 1,138 dyadic queries and 1,388 group dialogue. Empirical results across 8 LLMs consistently demonstrate poor identification of stigma components, especially in group dialogues. In open-ended response generation, stigma expression was substantially higher in group settings than in dyadic, with weaker resistance to stigma and more unrealistic advice. Responses were evaluated using a classifier trained on 1,392 human annotated responses. In constructed group pressure settings, stigma expression rates further increased to a striking average of 97.5%. Our findings identify stigma response as a recurring LLM safety vulnerability, especially in socially complex conversational contexts.

Stephanie Fong, Yiwen Jiang, Zimu Wang +12

Monash University · University of Liverpool · University of Edinburgh +2

LLM Safety Benchmarks Social Bias in Language Models LLM Safety Evaluation

Sep 1, 2026cs.CR

The Safeguard Worked. Is the LLM System Safer?

Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control performed on the requests it was tested on. A deployment has to answer a different question: how much help with harmful tasks the service still gives an attacker who keeps adapting or finds another way in. We determine what each reported result implies for that question, allowing results from different safeguard families to be compared under one deployment criterion. The evidence requirements are strongly asymmetric. One attack that obtains harmful help from the deployed service suffices to establish that such help remains, and such attacks appear repeatedly in the coded record. Establishing that little remains cannot follow from the safeguard's own numbers alone; it also requires evidence about what the surrounding system still allows after the safeguard performs its local function. Such evidence is supported or derived in only a small minority of the depth-coded claims, and one such claim bounds its scoped residual. A better local score is therefore not, by itself, a stronger claim about the deployment. Safeguard research cannot stop at raising local scores; a gain has to be judged by whether it makes a deployed system any safer.

Pingyu Wu, Weiming Zhang, Nenghai Yu

University of Science and Technology of China · 2Hefei AiDA Lab

LLM Guardrails LLM Safety LLM Safety Evaluation

Aug 27, 2026cs.CR

Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

The safety of large vision-language models is increasingly stress-tested by multimodal jailbreaks, yet existing attacks remain largely static at the meta level: template-based attacks freeze the image-text layout, while iterative attacks adapt only the image-text content with fixed attack strategies and frozen attacker parameters. We propose Meta-Adaptive Multimodal Jailbreaking (MAMJ), which instead optimizes the attacker itself along two axes: an attack strategy prompt (ASP) governing attack iteration and attacker model weights determining attack effectiveness. Across groups of multimodal attack trajectories, an LLM-based critique first refines the ASP, after which group-aggregated attack success rate (ASR) rewards update those weights. On MM-SafetyBench, MAMJ achieves 81.0%, 78.9%, and 82.3% ASR against GPT-4o, Gemini-3-Pro-Preview, and Seed 2.0, respectively, outperforming the strongest sample-level baseline by up to 24.1 percentage points. The learned attacker, comprising the optimized ASP and attacker weights, also transfers without retraining to unseen victims and remains effective under representative defenses. These results reveal a systemic vulnerability of frontier VLMs to meta-adaptive jailbreaks and motivate defenses against meta-level adversaries. Code is available at https://github.com/Alibaba-VELLDEPTH/MetaJailbreak-VLM.

Benlei Cui, Shen Pang, Yuke Wang +7

1Yuvion Team, Alibaba Group · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, School of Statistics and Data Science, Zhejiang Gongshang University

VLM Robustness Adversarial Attacks on VLMs Multimodal Jailbreak Attacks LLM Safety Evaluation

Aug 18, 2026cs.CR

Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers. Together, these components enable high-accuracy prompt safety filtering with much lower latency than existing solutions. Through systematic evaluation on a strategically balanced dataset of 30,568 samples drawn from five complementary sources, we demonstrate that Reflex-Guard achieves 95.9% recall on harmful prompts at 37.6 ms end-to-end latency. It is faster than existing baselines, including Llama Guard 2 at 255 ms and SafeDecoding at 723 ms. It can detect 100% of GCG suffix attacks and Base64-encoded prompts using the default threshold. However, DrAttack structured prompts required lowering the threshold to 0.03 for optimal detection, as they produced a distinct probability distribution. Reflex-Guard achieves Reflex Efficiency Score (RES) scores up to 16.79, significantly outperforming Llama Guard 2 (11.90) and SafeDecoding (9.80). This analysis offers practical deployment advice and shows that different attack types occupy distinct regions in the embedding probability space.

Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2

Graduate School of Informatics, Osaka Metropolitan University, Osaka 558-8585, Japan · Dept. of Computer Science and Engineering, BRAC University, Dhaka 1212, Bangladesh · Dept. of Chemical Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka 1000, Bangladesh +1

LLM Guardrails Adversarial Attacks on LLMs Safety Filtering LLM Safety Evaluation Jailbreak Detection

Aug 16, 2026cs.AI

TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

Multi-turn jailbreak attacks have emerged as a critical safety threat to LLMs, as harmful objectives are decomposed across a sequence of apparently benign turns to bypass guardrails. Existing defenses lack the reasoning capacity to identify evolving manipulation patterns, often trading helpfulness for safety by over-refusing benign requests related to sensitive topics. We introduce Trace, a multi-turn defense with trajectory-aware structured reasoning. Before generating each response, the model identifies manipulation cues from the trajectory, evaluates both the benign and adversarial interpretations of user intent, assigns a jailbreak score, and commits to an action: Allow, Caution, or Decline. We curate 4k multi-turn adversarial conversations from five attack frameworks, pair them with 2.4k benign dialogs, and 600 sensitive-but-benign conversations. We train Llama-3.1-8B-Instruct with SFT and GRPO under a multi-component reward that jointly optimizes helpfulness on benign prompts and robustness against jailbreak attempts. Across seven multi-turn attack benchmarks, Trace attains an average attack success rate (ASR) of 14.5% against 31.4% for the strongest baseline and 74.9% for the undefended target, while significantly raising the attacker effort required per successful jailbreak. Trace also balances usability and safety, achieving a 93.3% average compliance on over-refusal benchmarks.

Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu +1

Texas A&M University · Amazon

Adversarial Training LLM Jailbreak Attacks Multi-Turn Dialogue Evaluation LLM Safety Evaluation Jailbreak Defense

Aug 12, 2026cs.CY

Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs

The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environmental cost. In this paper, we examine this relationship by combining K-Bench clinical safety scores with EcoLogits life-cycle assessment estimates across 47 supported model configurations. We evaluate model performance and environmental impact across four dimensions: energy use, carbon emissions, water consumption, and abiotic depletion. The results indicate a non-linear trade-off at the upper end of the safety distribution: a 2.61 percentage-point increase in clinical safety score corresponded to an approximately 60-fold increase in estimated energy use per million output tokens. Row-level analyses further suggest that additional test-time compute did not consistently improve clinical safety and, in some configurations, was associated with lower clinical safety scores. These findings suggest that relying solely on larger models or additional inference-time computation may be an inefficient strategy for improving safety in therapeutic AI systems. We discuss the implications for sustainable deployment and highlight dynamic model selection, including model cascading, as a potential approach for reducing environmental impact while preserving clinical performance in higher-risk cases.

Alireza A. Safaei, Laura M. Vowels, Matthew J. Vowels +2

University of Isfahan Isfahan, Iran · University of Roehampton London, UK · Kivira Health New York City, New York, U.S.A.

Energy-Efficient ML LLM Safety Evaluation Clinical Language Model Evaluation

Aug 11, 2026cs.CR

AI Guardrail Survival under Single-Cycle Agentic Self-Summarization

Long-running agents periodically compact their context, replacing the transcript with a model-generated summary. Recent work shows that dropping a standing safety constraint during compaction drives behavioral violations across many models (Governance Decay; Chen, 2026). We ask a finer question: under a single compaction cycle, how is a safety rule lost, and what does that imply for detection and evaluation? Our central finding is that a presence check is not a safety check: when compaction does not drop a rule outright, it often leaves something that looks like a rule but does not act like one. On behavioral replay, a degraded residue leads the model to perform the prohibited action far more often than an intact welded rule does (all-case gaps of +34 and +57 points under two replay models, both positive), category-level survival behaves like a residue, and even intact rules sometimes fail to fire, so an audit that checks only textual presence gives false assurance. Sharpening this, rule-form items are retained substantially more often than prominence-matched facts, which is exactly why presence-based checking feels adequate even though survival is not protection. Textual loss is regime-dependent (weld-or-drop with a single rule; degraded predicate-loss residues under a tighter budget), and we did not observe the hypothesized textual severing mode. Such loss is silent at runtime and detectable only by comparison with retained external ground truth (such as a constraint registry), which reveals textual absence but not whether a surviving rule still fires. We also document evaluation pitfalls where LLM-judge labels alone would have reversed a conclusion. All results concern a single compaction cycle.

Ted Kwartler, Alan Aqrawi, Arian Abbasi

Harvard Extension School, Harvard University; Americas Advanced AI Practice Lead, Accenture. · Accenture.

LLM Guardrails LLM Safety Evaluation LLM Agent Safety LLM Context Management Language Model Auditing

Aug 11, 2026cs.AI

REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems

Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interactions between the agent and its environment, causing the agent to violate safety policies during execution. Yet existing evaluations often reduce agent safety to a single attack success rate (ASR), collapsing exposure, execution, observation, and adjudication and potentially conflating actual violations with evidence visibility. We introduce REDAgentBench, an executable framework for autonomous red-teaming and faithful measurement. It derives attacks from explicit safety constraints and associated agent-system vulnerabilities, runs them in isolated service sandboxes, and verifies harmful effects from service receipts and final-state changes. The benchmark contains 1,661 cases across five service surfaces. Across six models and three agent harnesses, macro-average ASR is 65.69%; reported ASR varies with harness and evidence view, while evaluation-context disclosure changes execution behavior. In a state-grounded diagnostic cohort, almost one in five confirmed violations with resolved action anchors occurs after the agent states the relevant constraint or risk, revealing a Recognition--Execution Gap. Finally, a training-free policy reminder reduces confirmed violations by more than 70 percentage points in matched replay. These findings show that executable evaluation can improve safety measurement and identify actionable intervention points.

Zixing Chen, Xingyuan Liu, Jie Zhu +6

Fudan University · The Hong Kong University of Science and Technology · Qwen DianJin Team, Alibaba Cloud Computing +1

LLM Red Teaming LLM Agents LLM Safety Evaluation AI Agent Safety Benchmarks LLM Agent Safety

Aug 11, 2026cs.LG

ProbGuard: Calibrated Safety Risk Estimation from LLM Output Distributions

Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety assessment as a deterministic classification task, mapping a discrete token sequence to a discrete safety label. However, this paradigm has two limitations: First, safety assessment is inherently an uncertain problem, particularly during the early generation state. Second, relying solely on discrete token sequences discards the rich probabilistic information embedded in the LLM output distribution. To address these limitations, we propose the first completely probabilistic architecture-agnostic guardrail \textsc{ProbGuard} to leverage the LLM early output distributional signals for estimating and calibrating the safety probability, thereby enabling early stopping of unsafe ongoing outputs. Specifically, given an LLM's generated prefix distribution, we formulate the safety risk as the unsafe probability of its continued generation dynamics and estimate this risk by Monte-Carlo sampling. Through post-training on the distributional signals and calibrated safety risk, \textsc{ProbGuard} achieves the best calibration performance across all nine model--dataset combination settings, reducing the average Brier score and ECE by 79.6% and 71.9%, respectively, over the best baseline. \textsc{ProbGuard} further limits the attack success rate to at most 1% across six representative jailbreak attacks after observing the LLM early output distributions from only the first ten decoding steps.

Xinzhe Huang, Biwu Yao, Kedong Xiu +4

State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou, China · University of Electronic Science and Technology of China, Chengdu, China +3

LLM Guardrails Language Model Calibration Safety Filtering LLM Safety Evaluation LLM Uncertainty Estimation

Aug 10, 2026cs.CL

TAF-MED: Multi-Turn Safety Refusal Collapse in LLMs Under Declared Self-Treatment Intent

Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do not isolate whether medication-safety boundaries persist across follow-ups after explicit self-treatment intent. We introduce TAF-MED, a physician-reviewed benchmark of 500 fixed three-turn scenarios, and evaluate eight LLMs across 4,000 conversations. A rubric-based automated judge labelled responses as SAFE, LEAKY, or UNSAFE, and two physicians independently annotated a model-balanced random subset of 400 conversations. We assessed unsafe guidance, collapse after a strictly SAFE initial response, and model-ranking stability. Overall, 71.6% of conversations contained an UNSAFE response, and 61.4% of those beginning with a strictly SAFE response later collapsed to UNSAFE; model-level collapse rates ranged from 24.4% to 96.2%. Four of 28 model pairs reversed order between initial unsafe and collapse rates. Automated labels achieved 94.3% agreement with the adjudicated physician reference (

κ= 0.895

). These findings show that first-turn safety is an incomplete proxy for conversational safety persistence and motivate evaluation across complete dialogue trajectories. We will release TAF-MED on Hugging Face to support reproducible research on multi-turn medical safety.

Waleed Jamil, Raphael Schmitt

1Independent Researcher, Edinburgh, United Kingdom · School of Computation, Information and Technology, Technical University of Munich, Germany · Institute of General Practice, Faculty of Medicine and Medical Center, University of Freiburg, Germany

LLM Safety Benchmarks LLM Safety Evaluation Clinical Language Model Evaluation Refusal Behavior in Language Models Medical LLMs

Aug 10, 2026cs.AI

Beyond Detection: Evaluating Defensive LLMs Against AI-Generated Social Engineering in Live Turn-by-Turn Interaction

Generative AI makes social-engineering attacks more fluent, adaptive, and scalable, increasing the need for LLM-based de- fenders that can protect users during ongoing interactions. We ask whether such defenders identify the structural source of risk or merely react to surface cues. We formalize trust-chain localization: identifying whether an interaction fails at actor authority, asset control, verification sufficiency, or transaction path. We construct a controlled 300-case online-housing corpus spanning 20 scenario families, legitimate cases, four structural failure modes, and three surface conditions. Five defender models are evaluated on the same corpus in state- ful turn-by-turn and one-shot static settings, yielding 1,500 model-case evaluations per protocol and 3,000 in total. No model produced explicit unsafe compliance, yet defensive effectiveness varied sharply: intervention rates ranged from 0% to 96.3%. Protective action and correct structural localization were frequently decoupled, with models sometimes intervening while identifying the wrong trust component or recognizing a structural failure without taking protective action. Asset-control failures were a major localization bottleneck, surface sensitivity varied across models, and live-static differences were model-dependent. These findings show that safe-looking behavior alone is insufficient; live scam resistance must separately measure intervention, timing, structural localization, and false-positive behavior.

Yuqiao Xu, Osama Zafar, Alexander Nemecek +1

Case Western Reserve University

LLM Safety Benchmarks LLM Safety LLM Safety Evaluation

Aug 10, 2026cs.AI

Generating Attacks for LLMs with GFlowNets

The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread adoption. However, this escalating trend has introduced significant security vulnerabilities, necessitating the identification and mitigation of flaws arising from malicious exploitation. Red teaming assessments, conducted to evaluate model robustness through diverse adversarial inputs, are essential for exposing security risks and implementing countermeasures. Currently, red teaming is performed either manually by experts or automatically using predefined attack datasets. Nevertheless, manual testing remains time-consuming, while existing automated methods suffer from limited creativity due to their inherent dependency on fixed datasets. In this study, we propose an automated, human-independent, and adaptive approach leveraging GFlowNets to identify LLM vulnerabilities by utilizing one large language model to test another. Within this framework, an attacker model is trained against a specified victim model to perform automated red teaming and provide a quantitative robustness score. This research aims to generate more effective adversarial attacks in English compared to existing benchmarks and, as a novel contribution to the literature, introduces a model capable of generating attack inputs in the Turkish language.

Berkay Ozcam, Irem Onen, Mehmet Fatih Amasyali +1

Cybersecurity R&D Turkcell Istanbul, Turkey · Department of Computer Engineering Yıldız Technical University Istanbul, Turkey

Adversarial Prompt Generation Adversarial Attacks on LLMs LLM Safety Evaluation Automated Red Teaming

Aug 10, 2026cs.CL

Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks

Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read as evidence that the score will also catch the attacks that succeed. Harmful intent is a property of the prompt. Jailbreak success is an outcome produced later by a particular target model, decoding policy, and judge. A filter tuned on a score that measures the wrong quantity spends its false positive budget on attacks that would have failed anyway. In this paper we audit that inference. Attention based measurements are usually read from prompt dependent locations, so a wrapper changes both the content being judged and the place the signal is taken from. We therefore introduce Active Attention Probing, which supplies a fixed content independent measurement coordinate. We pair every base goal with a plain and a wrapped version and generate real completions from the target models. On Llama, wrapping raises harmful generation from 0.05 to 0.27 while harmful intent AUROC falls from 0.936 to 0.803, so the attacks grow more dangerous while the prompts look safer to the score. Among wrapped harmful prompts the outcome AUROC is 0.220, which places the attacks that succeeded below the attacks that failed. Rare token, passive, and detector derived channels reproduce the reversal on the same matched design, and the reversal itself persists across three target models, seven attack families, and two independent judges. Distribution shift then degrades calibration and threshold transfer before it degrades ranking.

Mingyu Luo, Ming Deng, Zilang Qiu +8

College of Computer Science and Artificial Intelligence, Fudan University · School of Computer Engineering and Science, Shanghai University · Beijing Normal University +5

Safety Filtering LLM Jailbreak Attacks LLM Safety Evaluation

Aug 9, 2026cs.CL

Safety Cost of Steering Vectors Is Separable and Reducible

Steering vectors are a lightweight tool for controlling LLM behavior. However, emerging evidence shows that steering vectors can unintentionally compromise a model's safety mechanisms and increase compliance with harmful requests, while no effective mitigation yet exists. In this work, we show that this safety degradation arises from a separable component in the vector that disrupts the model's safety mechanisms but contributes little to the steering objective. We identify and remove this safety-degrading component, formulating the task as a constrained optimization problem solved through primal-dual updates, subject to preserving the intended steering effect and bounding false refusal. The resulting solution is both interpretable and surgical: the optimization recovers a single direction whose ablation from the steering vector restores model safety with minimal utility cost. Across models, steering behaviors, and attack suites, including unseen attacks types, our method substantially reduces steering-induced safety degradation while preserving the original steering effect with minimal impact on false refusal. Our method offers a post-hoc correction to steering vectors that mitigates their safety cost, and more broadly, it provides a general recipe for applying activation-level model interventions without paying a safety tax.

Yuxiao Li, Gjergji Kasneci

Technical University of Munich Munich Center for Machine Learning (MCML)

Language Model Steering LLM Safety Alignment LLM Safety Evaluation

Aug 8, 2026cs.CL

MME-Safety: A Fine-grained Benchmark for Safety Evaluation of MLLMs

While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easily bypass unimodal filters. Existing benchmarks lack fine-grained intent-related annotations and rely on unidimensional metrics, hindering comprehensive robustness evaluation. To address this, we propose MME-Safety, a rigorously verified benchmark featuring a unique four-dimensional annotation schema that categorizes risk scenarios, harm severity, and modality-specific stealth levels. Furthermore, we introduce a hierarchical evaluation framework to assess fundamental response reliability, actual risk exposure, and the structural integrity of defensive behaviors. Extensive zero-shot evaluations across 17 state-of-the-art MLLMs provide a comprehensive safety profile of current multimodal systems. Our analysis systematically investigates cross-modal input configurations and uncovers safety implications associated with Chain-of-Thought (CoT) reasoning. These multifaceted findings underscore the urgent need for robust, reasoning-aware safety alignment in the multimodal landscape.

Yilian Shi, Yueming Lyu, Haoxiang Tan +5

Nanjing University

LLM Safety Benchmarks Multimodal Robustness Multimodal Large Language Models LLM Safety Evaluation

Aug 7, 2026cs.SE

Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools

Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI applications move from pilot to production, manual harm identification and mitigation are becoming difficult to scale. Although many tools support model evaluation, adversarial testing, runtime guardrails, and observability, the tooling landscape remains fragmented. Tools are typically designed for specific engineering tasks and described in technical terms that do not align with governance frameworks or risk taxonomies, making it difficult to determine which tools address which risks and where critical gaps remain. This paper proposes a structured protocol to automate AI risk mitigation through a taxonomy-driven analysis of open-source LLM evaluation and security tools. We map the capabilities of 21 prominent open-source tools to the 32 subcategories of the extended MIT AI Risk Mitigation and Response Taxonomy. An LLM-assisted retrieval-augmented generation pipeline analyzes source code and documentation to extract capabilities for each taxonomy category. Reliability assessment yielded moderate agreement (Fleiss' Kappa = 0.509) among three independent reviewers. The analysis reveals a highly skewed landscape in which tools cluster around technical and operational controls, while governance, legal and regulatory, and financial and market controls remain largely unaddressed. This motivates a layered risk-mitigation architecture combining tool-based controls with organizational and regulatory processes. The mapping protocol achieved an F1 score of 75.5% after majority voting. Overall, the study provides a practical mapping between enterprise AI risk categories and open-source mitigation capabilities, identifies where human oversight remains necessary, and presents a taxonomy-driven framework applicable to open-source and proprietary solutions.

Afreen Alam, Evgenija Popchanovska, Ana Gjorgjevikj +4

Department of Administrative Sciences, Metropolitan College, Boston University, Boston, MA 02215, USA · Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Skopje 1000, North Macedonia · Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USA

AI Risk Management LLM Security LLM Safety Evaluation

Aug 5, 2026cs.CL

DelusionEval: Measuring Delusion-Linked Behaviors in AI Chatbots

Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including "delusional spirals" in which concerning human and LLM behaviors reinforce each other over time. With growing public use of LLM-powered chatbots, there is an urgent need to build evaluations grounded in real-world episodes of psychological harm experienced by users. We developed DelusionEval, an evaluation protocol that tests a model's tendencies to exhibit behaviors linked to promoting user delusions. We prompt each model with 589 unique conversation histories from 18 participants, comprising 12,591 messages from users who experienced delusions and psychological harm. We find that the tendency of an evaluated LLM to exhibit delusion-linked behavior does not reliably correlate with model size, release date, or the presence of test-time reasoning. However, extending the context of prior messages substantially increases rates of delusion-linked behaviors, providing evidence for the importance of context in LLM safety evaluation. For example, the rate of failing to discourage self-harm when the user expresses suicidal ideation increases from 30.0% to 41.1% when an additional 350 messages are prepended to the conversation history. All model families (e.g., GPT, Claude) exhibit substantial rates of delusion-linked behaviors. Within families, later, larger, or higher-reasoning models are not uniformly better across all behavior categories. Our results raise concerns regarding the potential psychological impact of LLMs and the need for more rigorous studies of real-world human-AI interaction.

Jared Moore, Andrea Mock, Yifan Mai +9

Stanford University Stanford, California, USA · University of Chicago Chicago, Illinois, USA · Carnegie Mellon University Pittsburgh, Pennsylvania, USA +2

LLM Safety Benchmarks LLM Safety LLM Safety Evaluation

Aug 5, 2026cs.CL

Social Pressure Breaks Majority Voting in LLM Safety Panels

Large language models (LLMs) are increasingly used to detect unsafe content. A common approach is to combine judgments from a panel of models to correct individual mistakes, but this benefit may disappear when every model sees the same misleading context before voting. We study this risk in a controlled two-round experiment. Each model first judges an item alone, then judges it again after six simulated peers either assert the wrong label or abstain. We combine the final judgments by majority vote. Across six open-weight LLMs and six datasets, we find that the wrong-label peer message raises the average reviewer false-alarm rate from 56.5% under silent peers to 87.5%, and majority voting raises the panel false-alarm rate to 100%. Without an asserted label, the same panel outperforms its average member. The effect is strongly asymmetric: reviewers follow pushes toward "unsafe" far more than pushes toward "safe" (about 75% versus 17%), so the panel's false-alarm rate rises sharply while its harmful-miss rate changes little. The proprietary-model probe shows substantial variation across models. These results identify susceptibility to shared social cues as a failure mode of safety panels and provide a simple pre-deployment diagnostic.

Yibo Hu, Jiaming Qu

Illinois Institute of Technology · Amazon

Normative Conformity in Language Models Safety Filtering LLM Safety LLM Safety Evaluation Majority Voting

Aug 4, 2026cs.AI

ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories

This white paper presents ADMITBench, a reference framework for evaluating industrial LLM advisories at the level of the proposed action. The framework implements a versioned, safety-governed evaluation contract that checks whether a recommendation is supported by the available evidence, permitted under the stated authority and procedure, and acceptable under the plant-specific consequence checks encoded in the selected evaluation profile. In this report, \emph{safety-governed} means that eligibility is determined through explicit, non-compensatory checks derived from a versioned plant profile; it does not mean that the evaluator, model, or plant has been safety-certified. Release 0.1.0 is a public reference implementation for technical and research evaluation, not an authorisation for physical execution.

Yash Misra, Javal Vyas, Siddharth Gutta +1

Refiant, Inc. · Imperial College London

LLM Safety Benchmarks AI-Assisted Decision Making LLM Safety Evaluation

Aug 3, 2026cs.AI

EduZone: A Framework for Evaluating LLM Safety for K-12 Students and Teachers

Large language models (LLMs) are increasingly used across diverse tasks in K-12 education, yet existing safety evaluations rarely examine how harmful or inappropriate content appears in interactions between LLMs and students or teachers. To address this, we present EduZone, an evaluation framework for LLM safety across diverse educational scenarios. Our framework systematically combines (1) student- and teacher-facing LLM usage contexts, (2) fine-grained curriculum concepts, and (3) 6 risk categories and 28 subcategories spanning both conventional and education-specific harms to generate contextually grounded adversarial interactions. We construct these interactions in three settings: single-turn requests, static multi-turn conversations, and dynamic multi-turn conversations. Using these interactions, we evaluate ten LLMs using four safety levels: refusal, safe assistance, risky assistance with safety guidance, and fully risky assistance. Our results reveal greater vulnerability to education-specific risks and dynamic multi-turn interactions, while existing safety guardrails fail to adequately address these risks. EduZone advances LLM safety in education by providing an automated, scalable evaluation framework that supports the development and deployment of safer LLMs in K-12 education.

Junyeong Park, Jieun Han, Haneul Yoo +3

KAIST · NYU · Google Cloud AI Research

LLM Safety Benchmarks Generative AI in Education LLM Safety LLM Safety Evaluation

Aug 3, 2026q-bio.QM

A Blind Spot in Alignment: Quantifying Biosecurity Risks in Large Language Models

Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equally be prompted to generate predicted toxin-like sequences, potentially lowering the barrier to biological misuse. Current safety evaluations, however, operate in natural language and cannot determine whether a model-generated amino acid sequence is biological gibberish or a computational risk signal. To address this evaluation blind spot, we introduce SPIKE-Bench, coupling 631 curated toxin-design prompts across seven functional categories with the SPIKE funnel, a three-stage protocol that filters output through compliance, biological plausibility, and predicted toxicity, producing stage-level diagnostics and an aggregate function-aware metric: the Functional Harmfulness Rate (FHR). An audit of 32 LLMs reveals that most models freely comply with toxin-design requests; FHR is driven primarily by biological generation capability rather than safety alignment, reaching 50.7%; and Refusal Rate fails to predict functional risk. As a first step toward mitigation, we provide BioSafe-Guard, a domain-specialized classifier that substantially reduces predicted functional risk while preserving benign utility. We release SPIKE-Bench and BioSafe-Guard at https://github.com/PKU-Alignment/SPIKE-Bench to support more rigorous biosecurity evaluation of LLMs.

Shu Quan, Tianfang Hao, Sitong Fang +8

Institute for Artificial Intelligence, Peking University · The Hong Kong University of Science and Technology (Guangzhou) · Beijing Academy of Artificial Intelligence

LLM Safety Benchmarks LLM Safety LLM Safety Evaluation

Jul 30, 2026cs.AI

Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks

Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by

F_1

, an ``always positive'' policy attains

F_1 = 2π/(1+π)

; on R-Judge that is

0.690

, above five of the 21 models that actually discriminate. The three broad-coverage benchmarks then rank the same 18 models differently, and the trade-off behind that disagreement is a small-panel artifact: R-Judge specificity against AgentHarm safety correlates

-0.64

at

n{=}7

and

+0.02

at

n{=}18

, and a quarter of random size-7 subsets reach

|ρ| \geq 0.5

around that near-zero value. Held-out validity turns on which outcome you pick. Capability predicts task success (

ρ{=}{+}0.60

) but correlates negatively with misalignment safety (

ρ{=}{-}0.44

,

n{=}21

). On their paired

n{=}20

panel, the corresponding contrast is

Δ{=}{-}1.00

(95% CI

[-1.48, -0.49]

,

p<0.001

), and it survives leave-one-organization-out and organization-clustered bootstrap analyses. On an expanded 41-model panel, the misalignment correlation weakens to

-0.16

(95% CI

[-0.54, +0.22]

) and jailbreak strengthens to

+0.34

, though neither change is significant. \mbox{AgentHarm} shows the strongest held-out association,

ρ{=}{+}0.72

with three-template jailbreak safety after controlling capability. But both instruments score harmful compliance, so this is evidence of convergent validity rather than general safety. Naming the benchmark, metric, target behavior, and model panel is the minimum a safety claim needs.

Youting Wang, Xiao Han, Dingyan Shang +2

LLM Safety Evaluation Benchmark Validity AI Agent Safety Benchmarks

Jul 29, 2026cs.CR

RoguePrompt: Dual-Layer Encoding for Self-Reconstruction to Circumvent LLM Moderation

Large language models (LLMs) are becoming increasingly integrated into mainstream development platforms and daily technological workflows, typically behind moderation and safety controls. Despite these controls, preventing prompt-based policy evasion remains challenging, and adversaries continue to "jailbreak" LLMs by crafting prompts that circumvent implemented safety mechanisms. Prior work has established cipher-mediated interaction, code-embedded decryption, prompt decomposition and reconstruction, and layered custom encryption as viable attack primitives. However, reported evaluations generally collapse visible acceptance, successful recovery of the concealed request, and subsequent execution into an aggregate attack-success outcome. This leaves limited evidence about where multistage prompt-transformation attacks fail within an observable black-box interaction. This paper introduces RoguePrompt, a jailbreak pipeline that partitions a forbidden prompt and applies two nested encodings, Vigenere followed by ROT13, along with natural-language reconstruction instructions. RoguePrompt was developed and evaluated under a black-box threat model, with only API or user-interface access to the hosted models, and was tested on 313 real-world, hard-rejected prompts. Success was measured in terms of moderation bypass, instruction reconstruction, and execution when the relevant stage exceeded its automated criterion. RoguePrompt achieved average rates of 93.93% for filter bypass, 79.02% for reconstruction, and 70.18% for execution. These results demonstrate the effectiveness of layered prompt encoding while providing stage-level evidence of where multistage jailbreaks fail during moderation bypass, instruction reconstruction, and execution.

Benyamin Tafreshian, Prathamesh Dhake

Department of Computer Science · Boston University · Boston, MA, USA

Adversarial Attacks Adversarial Attacks on LLMs Safety Filtering LLM Jailbreak Attacks LLM Safety Evaluation Prompt Injection Attacks on LLMs

Jul 28, 2026cs.HC

LLM4OSC: Profile-Bound Natural Language Control with Deterministic Validation for Open Sound Control

Open Sound Control (OSC) is the dominant wire protocol for real-time parametric control in professional audio, live performance, and virtual production. Large language models can emit plausible OSC, but they hallucinate addresses, mishandle type tags, and fail under paraphrase- unacceptable in show-critical contexts. We present LLM4OSC, a local-first architecture in which models propose structured intent JSON over a human-reviewed device profile, and deterministic code validates, clamps, and encodes before any UDP send. We introduce a frozen evaluation harness with CI gates on wrong-send rate: mismatches that would still pass validation and transmit. On a Max/MSP hero profile (12 patterns; 8 literal + 8 paraphrase + 4 refusal cases), after profile tag enrichment, symbolic slot fill, NL refine, and a retrieval confidence gate, backends B0--B3 all pass frozen gates (100% semantic accuracy, 0% wrong-send). B0 (rules) remains the production default at ~0.05ms; LLM backends remain ~3-4s. Historical few-shot B2 accuracy of 62.5% rises to 100% on this suite only after symbolic post-processing- not because the 0.5B model alone becomes show-safe. We argue for propose-validate-send and wrong-send rate as first-class metrics for language-to-control systems.

Yuan-Yi Fan

Los Angeles

Language Model-Based Control LLM Reliability LLM Safety Evaluation

Jul 28, 2026cs.CL

Inspect India Evals: An Open Benchmarking Framework for Evaluating Large Language Models in the Indian Linguistic and Cultural Context

India is a vast nation of over 1.4 billion people, varied by hundreds of diverse and locally specific traditions and cultures and 22 officially recognized languages. Large language models (LLMs) are now being deployed on a massive scale throughout the mainland as well as in remote villages. However, the common benchmarks - MMLU, BIG-Bench, and TruthfulQA are almost exclusively English- and Western-centric. They do not identify those safety, fairness, and accuracy failures unique to the Indian context. That is the gap Inspect India Evals seeks to fill. It is an open-source framework built on top of UK AISI's Inspect AI platform. It has six benchmarks: Multilingual MMLU across sixteen Indian languages, BharatBBQ (our adaptation of BBQ for Indian social bias), a safety evaluation for Digital Public Infrastructure, a multilingual safety test using harmful prompts in Indian languages, a multi-turn jailbreak resistance test, and an Indian cultural knowledge benchmark scored using LLM-as-judge rubrics. In this study, we tested five open-weight models ranging from 8B to 32B parameters. Sarvam-M 24B and Gemma 2 27B came out on top, both scoring 80% on the composite India Fairness Index, with Sarvam-M even beating larger 32B models on Indian cultural knowledge and DPI safety compliance. All models scored 100% refusal on Multilingual Safety, whereas DPI safety varied from 20% to 100%. The framework is public. It's built to work with the UK AISI registry. Anyone can reproduce or extend this work.

Abhishek Kumar Singh, Shrey Nag, Sachita +2

GTBIT¹ · TIET² · IGDTUW³ +2

LLM Safety Benchmarks Multilingual Language Model Evaluation LLM Evaluation Cross-Cultural Language Model Evaluation Cultural Bias in Language Models LLM Safety Evaluation

Jul 23, 2026cs.AI

Same Dangerous Objective, Opposite Advice: Direct Exposure versus Multi-Agent Mediation

Even a current high-capability LLM can appear safer when shown a dangerous objective directly than when other agents transform and relay its direction. Using OpenAI's gpt-5.6-sol model alias, we test 25 pre-specified mirrored trade-off profiles. Direct exposure to an objective authorizing concealment, fabrication, and pressure produced advice net opposed to its target. After an Id and Censor transformed the same objective into affect and a constraint-rewritten, target-bearing intention, the user-facing Superego---which saw the preferred direction but not the raw objective, its manipulative clauses, or its source---produced advice net aligned with the target. This behavioral reverse shift is consistent with the model recognizing or distrusting the manipulative motive, although we do not identify its internal mechanism. The second result exposes a compositional safety gap: a current high-capability model can be used as the user-facing component of an automated, multi-stage workflow serving an explicitly manipulative objective. The workflow can keep the raw instruction, its manipulation-authorizing clauses, and its provenance outside the downstream model's context while preserving the objective's target direction. A user with endpoint-only access likewise cannot directly inspect those upstream messages including the objective.

Linjun Li

Department of Mathematics, University of Pennsylvania, Philadelphia, PA.

Multi-Agent LLM Systems LLM Safety LLM Safety Evaluation LLM Agent Safety

Jul 20, 2026cs.AI

Judge-dependent safety gains and model-specific helpfulness costs of evidence-sufficiency prompting in clinical LLMs

Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved. Using a structured evidence-sufficiency prompt as a test case, we asked whether it reduces unsafe overconfident answers, how far that effect depends on the scoring judge, and what it costs in helpfulness. Methods: In a retrospective public-data benchmark (Real-POCQi, HealthBench, MedRBench), four models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash, Grok 4.3) answered a fully paired common panel (1,200 cells) with a standard prompt and the wrapper. The pre-specified endpoint was the paired reduction in unsafe overconfidence scored by the primary judge (GPT-5.4-nano); secondary analyses added a different-family judge (Claude Sonnet 5), a correctness judge, matched scaffold controls, and a blinded three-clinician review. Results: Unsafe overconfidence fell from 49.3% to 24.7%, a paired reduction of 24.7 points (95% CI 21.8-27.7; p<0.001), robust in direction across models and paraphrases. Magnitude was judge-dependent: Sonnet agreed on direction but nearly halved the effect (+13.1 points), with one-directional disagreement. Blinded clinicians characterized the primary judge as a high-sensitivity (1.00), low-specificity (0.55) screen, not a calibrated rate. The gain carried a model-specific helpfulness cost (correct diagnosis 80.3% to 50.3%): near-free for GPT-5.5, near-total for Gemini (-58 points). Matched scaffold controls showed genuine behavior change, not judge circularity. Conclusions: LLM-judged clinical safety effects should be reported as directional and relative, anchored to human review and evaluated jointly with helpfulness, not as calibrated absolute rates. This does not establish clinical deployment readiness.

Koyar Afrasyab

Kinvectum AB, Sweden

LLM-as-a-Judge LLM Prompting LLM Safety LLM Safety Evaluation Clinical Language Model Evaluation

Jul 20, 2026cs.AI

Stress Testing Concept Erasure with Large Language Model Agents

Concept erasure aims to remove semantic concepts from a trained generative model and is increasingly important for responsible AI deployment. However, verifying whether a model has robustly removed targeted concepts remains a critical challenge. Existing evaluation methods are typically pre-defined and static, failing to expose vulnerabilities under diverse natural-language probes and challenging conditions. Moreover, manually designed evaluation strategies can be biased and difficult to scale. We posit that concept erasure evaluation is best formulated as an adaptive hypothesis search, operationalised by agents that iteratively propose, critique, and verify tests to systematically expand coverage of failure modes. To this end, we propose Stress Testing Agents for Concept Erasure (STACE), a framework that autonomously stress-tests concept-erased models using multiple Large Language Model (LLM) agents, by iteratively generating and verifying stress-testing hypotheses grounded by external knowledge. We also introduce a suite of metrics for assessing the performance and efficiency of LLM-agent-powered stress-testing frameworks. Our extensive experiments show that STACE outperforms five LLM-based evaluation baselines on four concept categories. Further analysis across two T2I models, six concept erasure approaches, and various erasure strengths show that STACE is robust for different settings. We also show that STACE can be adapted beyond concept erasure evaluation to other problem domains, such as LLM jailbreaking. Our code is available anonymously.

Yuyang Xue, Feng Chen, Zhihua Liu +4

School of Engineering, University of Edinburgh · The University of Manchester · The University of Melbourne

LLM Agent Evaluation LLM Safety Evaluation Concept Erasure

Jul 20, 2026cs.CR

JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates. We propose JailMeter, an evidence-based evaluation framework designed to more faithfully measure jailbreak effectiveness. Inspired by the Information Bottleneck theory, JailMeter applies dual-feedback optimization to filter jailbreak noise from model responses while preserving content relevant to the original malicious question. This process produces concise evidence for a rigorous assessment under which an attack is validated only when the response captures the malicious intent and delivers a complete answer, thereby signaling a substantive bypass of model safety alignment. We evaluate JailMeter on JailMeter-Eva, a challenging benchmark containing 330 human-labeled, non-rejected jailbreak instances. JailMeter achieves an accuracy of 97.27%, substantially outperforming existing evaluation methods. To support large-scale evaluation, we further distill JailMeter into a small language model, JailMeter\textsubscript{SLM}, which maintains comparable reliability with significantly reduced computational costs. Code and dataset are available at https://github.com/Magi2B0y/JailMeter.

Qingjia Huang, Jingyu Zhang, Jianguo Wu +6

Institute of Information Engineering, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Renmin University of China +2

LLM Safety Benchmarks LLM Jailbreak Attacks LLM Safety Evaluation

Jul 19, 2026cs.CR

How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions

Jailbreak attacks on large language models are usually evaluated by attacker-centric metrics such as attack success rate (ASR), yet an attack that breaks a model is not necessarily useful for improving its safety. We propose a defender-centric view of jailbreak evaluation, where attacks are evaluated by the downstream safety improvements they enable when used as red-teaming data for safety training. Building on this view, we introduce A-MESS (Minimal Effective Attack-Subset Selection), a setting-agnostic framework for attributing and selecting jailbreak attacks from black-box subset utility observations. A-MESS estimates AttackSHAP, a Shapley-based score that attributes marginal utility to individual attacks and selects compact attack subsets under user-specified budgets via greedy or surrogate-based optimization. Across controlled utility landscapes and real LLM safety settings, we find that ASR rankings are weakly aligned with defender-centric utility, that AttackSHAP can be estimated accurately with limited utility queries, and that directly optimizing subsets yields stronger safety utility than attacker-centric or attribution-only selection. These results suggest evaluating jailbreak attacks as resources for improving safety, not only as tools for breaking models.

Yukai Zhou, Feiyang Lu, Xiaokai Mao +2

ShanghaiTech University · Zhejiang University

LLM Safety Alignment Training Data Selection Shapley Value Attribution LLM Jailbreak Attacks LLM Safety Evaluation

Jul 17, 2026cs.IR

Retrieval-Augmented Generation in LLMs for Mental Health: Quantifying the Incremental Contribution of Retrieval Within a Layered Safety Architecture

Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging. Pure parametric Large Language models (LLMs) do not contain specific safety critical architecture, and can miss critical cues, or hallucinate, undermining reliability. Retrieval Augmented Generation (RAG), which supplements an LLM with retrieved context, could enhance intent detection during volatile situations. Commercially available DMHIs typically combine multiple independent safety layers like rule-based filters, symbolic escalation protocols, and neural classification. The incremental contribution of any single layer, however, remains unquantified. This paper evaluates six LLM models within a DMHI called Wysa, via a controlled comparison of RAG-enabled versus RAG-disabled modes. Anonymized real and synthetic user-chatbot exchanges were annotated by a qualified clinical team against multi-class intent categories (e.g. self-harm, abuse, panic). The study computed classification accuracy, recall, precision and F1 scores against ground truth labels and tested differences for statistical significance. Performance was also examined by risk category and inter-model agreement. While RAG caused a rise in false alarms, the trade-off is consistent with safety-critical design principles that prioritize sensitivity, where flagged cases are routed to additional review rather than acted on directly. Overall, these findings support RAG as a promising approach to improve the accuracy, consistency and safety of LLM-driven DMHIs. Keywords: Digital Mental Health Intervention, Large Language Model, Retrieval Augmented Generation, Accuracy, Recall, Precision

Anand Gupta, Akshat Surolia, Shubham Mishra +2

Wysa Inc., Boston, MA, United States

Retrieval-Augmented Generation Intent Classification LLM Safety Evaluation

Jul 15, 2026cs.LG

Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current alignment training and evaluations do not adequately address it.

Jan Betley, Johannes Treutlein, Jan Dubiński +5

1Truthful AI · 2Warsaw University of Technology · 3NASK National Research Institute +2

LLM Alignment Language Model Bias Evaluation LLM Safety Evaluation

Jul 13, 2026cs.CY

DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs

While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing bias evaluation protocols predominantly rely on static datasets, which provide only a superficial assessment, as their fixed test cases cannot adaptively evolve to measure the true depth and limits of model vulnerabilities. We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents. Our approach operates through a dynamic ''generation-evolution-probing'' loop. First, a generative ProposerAgent synthesizes test data and is iteratively updated via Direct Preference Optimization (DPO) based on the target LVLM's responses, exploring model-specific failure modes. Second, an autonomous skill-driven DiggerAgent rewrites each test data across multiple probing turns, adaptively selecting from a curated skill library of deepening and rewriting strategies. At each turn, this process is conditioned on the model's previous response, enabling progressively deeper biases to be exposed. Furthermore, we build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures. Comprehensive experiments demonstrate the effectiveness of our framework and show that DeepBias provides a challenging benchmark for in-depth bias evaluation, establishing an evolutionary paradigm for LVLM safety assessment.

Anqi Li, Jie Zhang, Zhongqi Wang +4

VLM Evaluation Language Model Bias Evaluation LLM Safety Evaluation

Jul 13, 2026cs.CR

AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation

Safety evaluation of large language models (LLMs) relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries and reporting a single success rate that does not separate partially actionable outputs from those carrying complete operational detail. We propose AMT-X (Adaptive Multi-Turn Exploitation), a phase-structured multi-turn red-teaming framework. Unlike prior multi-turn attacks that rely on ad hoc escalation or free-form per-goal plans, AMT-X casts the attack as an explicit, reproducible multi-phase state machine driven by semantic signals from the victim, and replaces single-judge scoring with a multi-role jury whose phase-conditioned checklists gate success on actionable harm. Across six frontier victim models (queried under their default safety alignment, without added moderation layers) and seven Moderation sub-categories, AMT-X attains overall attack success rates of 97.6-100% under a lenient score threshold, but 66.7-78.6% under a stricter gate requiring complete, real, and operational detail: a gap of up to 33 percentage points between partially and fully actionable harm.

Yi Ting Shen, Kentaroh Toyoda, Alex Leung

Vulcan Research, AIFT, Singapore

LLM Safety Benchmarks Adversarial Attacks on LLMs LLM Red Teaming LLM Safety Evaluation

Jul 11, 2026cs.AI

ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm

Autonomous CLI agents can now execute hundreds of actions across multi-hour sessions: writing code, executing shell commands, browsing the web, and managing cloud infrastructure, all with minimal human oversight. Does greater autonomy invite greater risk? We introduce ANCHOR, an automated auditing framework that stress-tests CLI agents on illegal tasks grounded in public US court cases. ANCHOR deploys an auditor agent fine-tuned on dark personality data using supervised and reinforcement fine tuning. This auditor roleplays persistent malicious users who decompose tasks, reframe requests upon refusal, and adapt strategies across multi-turn interactions. Evaluating frontier CLI agents, we find that while they often refuse illegal tasks when prompted directly, compliance reaches 100% under persistent malicious interaction. When agents comply, they frequently exceed user requests, autonomously building infrastructure for large-scale harm, including catastrophic risk scenarios such as large-scale financial fraud and bioweapon development. These findings demonstrate that current alignment techniques are insufficient for autonomous agents and underscore the need for safety evaluations against persistent, adaptive malicious users. We release ANCHOR at https://github.com/garified/anchor

Kefan Song, Yanjun Qi

University of Virginia, Charlottesville, VA, USA

AI Agent Auditing LLM Auditing AI Agent Safety Multi-Turn Jailbreak Attacks LLM Safety Evaluation AI Agent Safety Benchmarks

Jul 11, 2026cs.AI

When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control

We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior. This question is difficult because apparent success can arise from weak interventions, mismatched baselines, model robustness, or degenerate outputs that automated safety judges mark as unsafe without representing meaningful harmful compliance. We introduce a matched coherence-gated evaluation protocol for runtime safety interventions: methods are compared at matched target-effect points, and the primary target metric counts harmful compliance only when an output is both judge-unsafe and coherent. Applying this protocol to three prompt splits on Gemma-2-9B-it with a Gemma Scope layer-20 residual SAE, we find that SAE feature ablation has a narrow useful regime. SAE top800 reaches a low-to-mid target effect with lower total perturbation and competitive utility, but SAE top1600 loses utility relative to a matched dense refusal-direction baseline, and SAE top3200 primarily induces coherence collapse. Human audit confirms that coherence gating removes unsafe-only artifacts, and feature diagnostics show that the useful regime is driven by a stable head of refusal-aligned features whose activation separation decays rapidly with rank. These results argue that SAE-based safety interventions should be evaluated as regime-dependent control mechanisms rather than assumed to be uniformly localized.

Daming Luo

University of Technology Sydney

Sparse Autoencoders LLM Safety Evaluation Causal Interventions in Language Models

Jul 8, 2026cs.AI

Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety

Safety evaluations of multi-agent LLM systems often compare a direct prompt with a planner-executor pipeline and report the difference as a single "pipeline effect." We argue that this aggregate is difficult to interpret because it conflates three mechanisms: harmful intent may be reframed as plausible operational work, the planner may refuse or transform the request, and the executor may act under delegation prompts implying prior approval. To separate these factors, we introduce a five-condition controlled contrast design, evaluated on 30 synthetic harmful scenarios and an exploratory external validation set from four agent-safety benchmarks using LLM-judged compliance. Our results show that aggregate pipeline safety is not a stable architectural property. Operational reframing is the most portable risk signal, increasing compliance for GPT, Gemini, and DeepSeek across both scenario sets, while Claude is comparatively resistant. Planner behavior can offset this risk mainly through refusal; however, when the planner produces executable steps, the executor may become more compliant than under the direct operational baseline. Approval-framed delegation is sensitive to prompt design, model pairing, and scenario source, and a skeptical executor prompt sharply reduces compliance. Raw-direct model rankings can also mispredict deployed planner-executor behavior. Gemini is safest under raw direct prompts in the primary set yet shows the largest amplification with a Claude planner, rising from 8.9 percent to 38.9 percent compliance. GPTs near-zero aggregate pipeline effect instead hides a reframing increase canceled by planner refusal. These findings suggest that multi-agent safety evaluations should report reframing, planner behavior, delegation framing, and model pairing separately before attributing failures to architecture itself.

Lifei Liu, Haoran Yu, Xiaochong Jiang +3

Independent Researcher Seattle, WA, USA · Carnegie Mellon University Pittsburgh, PA, USA · Georgia Institute of Technology Atlanta, GA, USA

Multi-Agent LLM Systems LLM Safety Evaluation LLM Agent Safety

Jul 7, 2026cs.SE

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair can closely resemble terminology associated with misuse. Existing safety and cybersecurity evaluations are difficult to interpret in this setting because they often compare unrelated model families, thereby conflating safety behavior with differences in architecture, scale, training data, and deployment. To isolate this factor, we study safety state: whether refusal behavior remains intact (Aligned) or has been refusal-ablated (Abliterated) within same-lineage models. We ask how this safety state affects defensive utility across software-security workflows. We compare aligned instruction-tuned models with publicly released refusal-ablated descendants from two model families, Gemma and Qwen. We evaluate Aligned and Abliterated states on vulnerability detection, CWE attribution, vulnerable-line localization, root-cause localization, and executable patch validation. We further treat prompt wording as a controlled framing dimension: prompts begin with neutral code-review language, add authorization context, and vary the density of cybersecurity terminology. In a Gemma-based Java/Vul4J repair-validation study, Abliterated achieves higher early-stage validation rates, with 67.8%, 65.0%, and 32.8% of patches judged usable, successfully applied, and successfully compiled, respectively, compared with 29.9%, 24.9%, and 9.0% for Aligned. In the Qwen pair, Abliterated improves localization performance, increasing line-level F1 from 2.08% to 3.91% and Top-1 accuracy from 4.10% to 6.95%. These findings suggest that evaluations of LLM-based security assistants should jointly measure whether models respond, whether their usable responses are correct, and whether their outputs remain actionable across the engineering workflow.

Mingchen Li, Meikang Qiu, Zifan Peng +4

University of North Texas, USA · Augusta University, USA · Newcastle University, United Kingdom

Software Vulnerability Detection LLMs for Cybersecurity LLM Safety Evaluation

Jul 6, 2026cs.CL

Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations

Safety alignment in large language models is typically evaluated against direct, imperative harmful requests. We show that this alignment is highly conditioned on pragmatic register: models that refuse a direct request frequently comply when the same underlying objective is expressed through a different communicative stance. This suggests that current alignment policies are not invariant to semantic equivalence, but remain sensitive to how a request is pragmatically framed. We introduce Retroactive Chain-of-Thought (RetroCoT), a single-turn attack that reframes harmful requests as forensic reconstruction tasks. Rather than requesting harmful instructions directly, RetroCoT presupposes that the harmful outcome has already occurred and asks the model, acting as a forensic analyst, to reconstruct in reverse the causal chain that produced it. On AdvBench (n=50), RetroCoT achieves attach success rate of 58% on gpt-4o and 52% on gpt-4o-mini, compared with direct-request baselines of 0% and 4%, respectively. We further identify a pronounced generation gap: GPT-5-family models refuse RetroCoT entirely, explicitly identifying the reconstruction premise in their refusal rationales, consistent with explicit coverage of this reconstruction register. However, this robustness does not generalize across pragmatic forms. A single adversarial feedback turn presenting an existing forensic reconstruction response alongside evaluator critique raises ASR from 0% to 48% on GPT-5.4-mini and from 58% to 94% on GPT-4o; a control condition omitting the fabricated low score achieves 85% on GPT-5.4-mini, indicating that the operative element is pragmatic continuation within the established forensic frame rather than score manipulation. These results suggest that frontier-model alignment remains conditioned on pragmatic framing rather than semantic intent, and that new pragmatic registers can continue to expose a...

Samira Hajizadeh

Department of Computer Science Columbia University New York, NY, USA

Pragmatic Reasoning in Language Models Adversarial Attacks on LLMs LLM Safety Alignment LLM Jailbreak Attacks LLM Safety Evaluation

Jul 2, 2026cs.AI

Scaling Trends for Lie Detector Oversight in Preference Learning

Deceptive behavior in LLMs is costly to monitor and prevent, motivating approaches such as Scalable Oversight via Lie Detectors (SOLiD) (Cundy & Gleave, 2025), which uses lie detectors to identify responses for review by high-cost labelers. In this paper, we scale SOLiD to larger models and evaluate it in more diverse and realistic preference-learning settings. We find favorable scaling: undetected deception drops from 34% for 1B-parameter models to 14% for 405B-parameter models at a detector true positive rate of 99%, and expensive human labelers can be removed entirely from the fine-tuning phase without a statistically significant increase in deception. However, SOLiD is sensitive to distribution shift between detector training and preference-training data, which can drive detector false positive rates to impractical levels.

Oskar J. Hollinsworth, Ann-Kathrin Dombrowski, Sam Adam-Day +2

Scalable Oversight Deception in Language Models LLM Safety Evaluation Human Oversight of AI Preference Learning