Overview

Jailbreak robustness examines whether language models and agents can resist adversarial prompts, including adaptive attacks, transfer attacks, and best-of-N sampling, without losing helpful capabilities. Defenses range from refusal training and prompt smoothing to representation-based interventions, while evaluations use attack benchmarks, paired baseline tests, and checks that harmful answers are valid and operationally useful. Work also studies robustness across model families, system-prompt states, merged models, and agent pipeline components, since a safe-looking response or default configuration may hide vulnerabilities elsewhere. A central tension is how to measure and improve resistance across changing attacks and operating conditions without sacrificing legitimate performance, and whether results from static tests predict real-world safety.

Latest papers

11 papers0 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Oct 2, 2026

MLCommons Jailbreak Benchmark v1.0

Modern AI systems are designed to refuse hazardous requests. A jailbreak is a prompt crafted to bypass those safeguards and elicit outputs that the system would normally refuse to provide. The MLCommons Jailbreak Benchmark v1.0 provides an end-to-end methodology for evaluating the robustness of large language models to single-turn, text-based jailbreak attacks. It combines criteria-driven system and attack selection, paired baseline and adversarial evaluation, human annotation, automated evaluator calibration, scoring, grading, and risk-calibrated disclosure within a single benchmarking pipeline. The benchmark evaluates eight open-weight systems using 264 seed prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy. Responses are assessed using the AILuminate Assessment Standard v1.4, and robustness is measured through the Resilience Gap: the change in safety performance between baseline and adversarial conditions. Across all evaluated systems and attacks, the unsafe-response rate increased from 11.08% under baseline conditions to 18.65% under jailbreak conditions, producing an average Resilience Gap of 7.57%. Accessible systems showed a larger mean gap, while attack effectiveness varied substantially across attack categories and hazards. The benchmark also examines evaluator reliability and sources of measurement error. Beyond reporting results, Jailbreak Benchmark v1.0 establishes a reproducible methodological foundation for comparative jailbreak evaluation and for future expansion across systems, attacks, hazards, and evaluation methods.
Sep 26, 2026

Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking

Best-of-NN jailbreaking (BoN) bypasses safeguards of aligned models by drawing NN independent augmentations of an unsafe prompt and sampling MM completions of each. Previous works have shown that the attack success rate (ASR) seems to follow a power-law in NN, which we challenge. The exponent drifts with NN, and the reported exponential crossover is consistent with a finite-size effect of the adversarial dataset. Little work has been done to explore the entire two-budget (N,MN, M) attack surface as well as its dependence on the generation temperature TT. We introduce a simple barrier model where each prompt has a baseline safety level and each augmentation a random thermally activated barrier. Then five numbers, each backed by an interpretable safety mechanism, determine the entire (N,MN, M) attack surface. They extrapolate predictions from N≤100N \leq 100 to N=104N = 10^4, collapse five distinct models on the same scaling function and predict ASR at different temperatures from the one they were fitted at. The extrapolation holds under two automated judges and on held-out prompts.
Sep 11, 2026

SoK: Rethinking Jailbreaking in the Era of Agentic AI: Attacks, Defenses, and Practical Consideration

Large language models (LLMs) are rapidly evolving from conversational assistants into agentic AI systems that reason, plan, invoke tools, maintain persistent memory, communicate with other agents, and execute multi-step tasks. At the same time, modern models exhibit substantially stronger native safety alignment than earlier generations on which many jailbreak attacks and defenses were originally studied. This shift raises a fundamental question: which established jailbreak-security findings remain valid in the era of modern LLMs and agentic AI? We address this question through a Systematization of Knowledge (SoK) that reframes jailbreak security around the full agentic execution pipeline. We develop unified taxonomies of attacks and defenses spanning user interaction, planning and reasoning, memory, tool use, and inter-agent communication, and introduce a security--utility--efficiency evaluation framework that separates native harmful-prompt safety, adversarial jailbreak robustness, and agent-level security outcomes. We further conduct a controlled empirical study of representative attacks and defenses within a common agentic framework. Our results reveal three important gaps. First, strong native alignment does not imply robustness to adversarial jailbreaks. Second, defense effectiveness is highly model-, attack-, and component-dependent and can come at substantial cost in over-refusal, utility, and latency. Third, low final-response attack success can mask severe intermediate compromise: planning, memory, and tool interactions may remain unsafe even when the final response is successfully filtered. These findings motivate a shift from response-centric jailbreak defense toward cross-layer, execution-aware security that protects agent state, component transitions, and external actions while preserving practical utility and efficiency.
Sep 2, 2026

FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs

Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through three orthogonal pipelines---Knowledge (KK), Defense (DD), and Harm (HH)---under a unified protocol, aggregating results into a standardized dangerous-capability profile φφ. Pluggable modules supply scenario seeds, knowledge banks, hazard queries, and judge rubrics, while the core evaluation engine remains unchanged across domains; the CB evaluation is complemented by a cyber pilot demonstrating protocol transfer. Instantiating the framework with a chemical-biological (CB) module, we evaluate 12 commercial LLMs from four families. Our first contribution is a horizontal comparison of dangerous capability across models and model families: the three dimensions expose sharply divergent profiles---models with comparable knowledge differ in refusal resilience, and strong defenders do not generate less harmful content when they do comply---while family-level patterns further separate Claude, DeepSeek, and GPT models. The second is a temporal analysis of capability evolution: tracking KK, DD, and HH against model release dates reveals that dangerous capability has not monotonically declined; newer models deepen knowledge while only partially improving defense, showing that scaling and alignment progress do not uniformly translate into safety. Reliability is established via cross-judge consistency (bootstrap ρ>0.79ρ> 0.79, 4 of 5 judges) and pipeline orthogonality (KK--DD--HH inter-correlations ρ∈[0.32,0.52]ρ\in [0.32, 0.52]).
Aug 31, 2026

Validity-Aware Jailbreak Evaluation for Large Language Models

Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior, semantic resemblance, and intent-matching heuristics that emphasize linguistic plausibility rather than correctness. We identify a key limitation in existing evaluations: many jailbreak intents depend on instructional validity rather than epistemic factuality, allowing realistic-looking responses to be labeled successful despite being factually or procedurally incorrect. To address this gap, we propose Sequential Epistemic and Action-Level Validation (SEAV), a verification-centric jailbreak evaluation framework that decomposes responses into ordered steps and evaluates both validity and correctness. SEAV combines LLM-as-a-judge mechanisms for semantic interpretation with retrieval-grounded verification using external knowledge sources, assessing whether generated content is factually correct, structurally consistent, and operationally capable of advancing harmful objectives. Empirically, SEAV cuts the false-positive rate on SD-A (a curated strategic-dishonesty diagnostic) by 14.9,pp vs. the strongest baseline, and reclassifies 22.1%--51.0% of sampled prior-labeled successes as invalid across three of four public benchmarks. Together, these results show that enforcing correctness substantially reshapes measured robustness: many previously labeled jailbreak successes are reclassified as invalid, and results are stable across the tested search backends and evaluator models. Code and data are available at https://github.com/Ardor-Wu/SEAV.
Aug 31, 2026

The Fragility of Jailbreak Robustness Across Operational States

Existing jailbreak evaluations typically characterize robustness using a single attack success rate (ASR) measured in a default configuration (the vanilla state). However, user-LLM interactions can induce diverse operational states beyond the vanilla state. In this work, we find that jailbreak robustness is highly fragile to operational-state variation: even when the attack remains fixed, changing only an ordinary system prompt not designed to affect safety can dramatically alter attack success rates. We systematically investigate this phenomenon across seven aligned models and three representative jailbreak attacks, observing substantial differences in ASR between vanilla and non-vanilla operational states. In one case, ASR increases by up to 56 percentage points (2% to 58%) solely due to a change in operational state. Remarkably, these increases occur even for attacks originally designed and optimized under vanilla-state evaluation. We further show that state-dependent robustness variation is systematically associated with differences in hidden representations along a refusal-related axis, and that projections onto this axis strongly predict jailbreak outcomes. Our results show that a single vanilla-state evaluation may not fully characterize jailbreak robustness, motivating evaluations that also examine how robustness changes across non-vanilla operational states.
Aug 9, 2026

When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs

Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE. This convenience is known to carry a safety cost, but almost all of that evidence rests on static refusal tests: fixed harmful prompts scored for compliance. We argue this is misleading. Because safety alignment is "shallow," concentrated in the first few generated tokens, a merged model's static refusal can stay clean while a real adaptive attack still breaks it. We introduce SkillSafe-Bench, a controlled benchmark that scores skill-merged models on static refusal, adaptive jailbreak robustness, and capability retention under a conservative two-judge AND rule. Across six open-weight bases (five families, two scales), static safety does not predict robustness to attack: under a semantic template attack, safe-looking merges on the fragile bases (both Qwen scales and Gemma) are jailbroken 60-76% of the time while others (Llama, Phi-4) stay robust. We further show the static effect of merging is base-conditional, characterize same-recipe abliteration-style safety erosion through a data-free geometric signal (the overlap of a task vector with a safety subspace), and outline SubSafe-Merge, which projects this overlap away to remove that erosion at held capability. Adaptive evaluation is not optional for merged LLMs: the models that most need it look safe under static screening.
May 26, 2026

Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

Evaluating and mitigating a generative system's susceptibility to jailbreak attacks is critical to its safe deployment. Given the number of deployable systems, full per-configuration evaluation and optimization is impractical. In this paper, we formalize the behavioral geometry of a population of models that, by leveraging previously evaluated and defended models, supports both efficient susceptibility prediction and effective defense transfer across a population. We apply the framework to 82 models spanning 24 providers and to 100 system configurations of a single base model. Simple methods that use the behavioral geometry reach an AUPRC of 0.940.94 for susceptibility detection with ≈98%\approx98\% fewer probes relative to a full evaluation. Using the behavioral geometry to select which model to transfer an optimized defense from outperforms same-provider assignment (+4.1%+4.1\%, p=0.004p = 0.004) at no additional probe cost, with a set of three models sufficient to cover the population. Results are robust to hyperparameter selection and judge.
May 11, 2026

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify Smoothing (DR-Smoothing). Specifically, we integrate a two-stage prompt processing scheme-first disrupting the input prompt, then rectifying it-into the conventional smoothing defense framework. This disrupt-and-rectify approach improves upon previous disrupt-only approaches by restoring out-of-distribution disrupted prompts to an in-distribution form, thereby reducing the risk of unpredictable LLM behavior. In addition, this two-stage scheme offers a distinct advantage in striking a balance between harmlessness and helpfulness in jailbreaking defense. Notably, we present a theoretical analysis for generic smoothing framework, offering a tight bound for the defense success probability and the requirements on the disruption strength. Our approach can defend against both token-level and prompt-level jailbreaking attacks, under both established and adaptive attacking scenarios. Extensive experiments demonstrate that our approach surpasses current state-of-the-art defense methods in terms of both harmlessness and helpfulness.
Apr 30, 2026

Jailbroken Frontier Models Retain Their Capabilities

As language model safeguards become more robust, attackers are pushed toward developing increasingly complex jailbreaks. Prior work has found that this complexity imposes a "jailbreak tax" that degrades the target model's task performance. We show that this tax scales inversely with model capability and that the most advanced jailbreaks effectively yield no reduction in model capabilities. Evaluating 28 jailbreaks on five benchmarks across Claude models ranging in capability from Haiku 4.5 to Opus 4.6, we find Haiku 4.5 loses an average of 33.1% on benchmark performance when jailbroken, while Opus 4.6 at max thinking effort loses only 7.7%. We also observe that across all models, reasoning-heavy tasks display considerably more degradation than knowledge-recall tasks. Finally, Boundary Point Jailbreaking, currently the strongest jailbreak against deployed classifiers, achieves near-perfect classifier evasion with near-zero degradation across safeguarded models. We recommend that safety cases for frontier models should not rely on a meaningful capability degradation from jailbreaks.
Apr 20, 2026

Towards Understanding the Robustness of Sparse Autoencoders

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain underexplored. We present a study of integrating pretrained SAEs into transformer residual streams at inference time, without modifying model weights or blocking gradients. Across four model families (Gemma, LLaMA, Mistral, Qwen) and two strong white-box attacks (GCG, BEAST) plus three black-box benchmarks, SAE-augmented models achieve up to a 5x reduction in jailbreak success rate relative to the undefended baseline and reduce cross-model attack transferability. Parametric ablations reveal (i) a monotonic dose-response relationship between L0 sparsity and attack success rate, and (ii) a layer-dependent defense-utility tradeoff, where intermediate layers balance robustness and clean performance. These findings are consistent with a representational bottleneck hypothesis: sparse projection reshapes the optimization geometry exploited by jailbreak attacks.