Adversarial Attacks on LLMs

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

37 papers in the last four weeks, up 311% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 238

Jun 3, 2026cs.AI

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories

Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs. Recent work attributes this to shallow safety, where alignment concentrates in the first few output tokens. We show that shallow safety is a special case of a broader inference-time vulnerability, in which short token injections at any generation step can substantially alter subsequent safety behavior. We also find that a model's alignment with refusal directions in its hidden states does not predict its robustness to such injection, revealing that internal state alone does not determine generation behavior under perturbation. To address this, we align models directly on generation trajectories constructed by simulating mid-sequence perturbation, and show that this improves robustness to mid-sequence injection and generalizes to attacks that exploit early-token generation. Our work argues that robust safety alignment requires training on the generation process itself, not only its outputs.

Kyungmin Park, Taesup Kim

Hankuk University of Foreign Studies · Seoul National University

Adversarial Attacks on LLMs LLM Safety Alignment Adversarial Robustness of Language Models Inference-Time Language Model Alignment

Jun 2, 2026cs.LG

When Autoregressive Consistency Hurts Safety Alignment

Safety alignment in large language models (LLMs) is fragile in part because it is often shallow: fine-tuning mainly reshapes the model's behavior near the first few output tokens. We argue that this phenomenon can be understood through autoregressive consistency, the tendency of next-token prediction to preserve and extend the current response trajectory consistently. By analyzing the learning dynamics of safety alignment, we show that autoregressive consistency can concentrate alignment updates on early tokens, offering a mechanistic explanation for shallow safety alignment. The same mechanism also predicts a broader class of attacks on LLMs: attacks that induce harmful continuation states at arbitrary positions in the output trajectory. As a concrete example, we introduce random insertion attack, which inserts a short harmful span into an otherwise safe refusal trajectory and exploits autoregressive consistency to sustain the resulting harmful branch, thereby bypassing safety alignment. Notably, a short harmful span can redirect the generation to be harmful even after a long refusal prefix, highlighting autoregressive consistency as a potential broader failure mechanism. This suggests that safety alignment should also break harmful autoregressive consistency throughout the output trajectory. We therefore propose adversarial safety alignment, an initial framework based on worst-case harmful continuation states, and instantiate it with random worst-insertion training. Overall, our results suggest that autoregressive consistency should be treated as a central consideration in both safety alignment and attack design.

Bochen Lyu, Yiyang Jia, Xiaohao Cai +1

University of Southampton · Independent Researcher

Adversarial Attacks on LLMs LLM Safety Alignment LLM Safety

Jun 2, 2026cs.CR

Testing LLM Arithmetic Reasoning Generalization with Automatic Numeric-Remapping Attacks

Large language models achieve strong performance on arithmetic reasoning benchmarks, and one common response to arithmetic brittleness is to delegate computation to code. Yet models are still often used in settings where they must reason directly from natural language, and trustworthy models should solve small-number arithmetic word problems without external tools. Prior work shows that LLMs are sensitive to numerical variation: a model may solve an original problem but fail on structurally similar variants requiring the same reasoning procedure with different numbers. We ask whether this fragility persists under a stricter setting involving small, schema-preserving numeric changes that retain the original reasoning program and avoid large-number stress tests. We introduce an automatic algorithm for generating numeric-remapping attacks on arithmetic word problems. Unlike template-based perturbation methods requiring manual schemas or constraints, our approach derives problem-specific symbolic representations, generates constrained numeric remappings, recomputes gold answers, and realizes transformed questions through deterministic edits guided by LLM-generated edit plans. Stage-wise validation and a high-confidence audit retain reliable attacks, making the pipeline scalable with limited human intervention. We evaluate DeepSeek-R1 (70B), Gemma4 (31B), and GPT-OSS (120B) on GSM8K, MAWPS, and MultiArith. On GSM8K, completed runs show conditional accuracy drops of 12.16 to 25.82 percentage points. MAWPS and MultiArith are far more stable, with most attacked accuracies near or above 98%. These results show that numeric-remapping robustness depends strongly on dataset structure: GSM8K remains sensitive even when reasoning programs are preserved and answers are recomputed, while shorter, more regular datasets are more robust.

Malia Barker, Bishal Lakha, Edoardo Serra +1

Department of Computer Science, Boise State University, Boise, ID, USA · University of L'Aquila, L'Aquila, Italy

Numerical Reasoning in Language Models Mathematical Reasoning Benchmarks Adversarial Attacks on LLMs LLM Reliability Language Model Robustness LLM Mathematical Reasoning

Jun 2, 2026cs.CR

PsychoPass: Geometric Profiling of Multi-Turn Adversarial LLM Conversations

Multi-turn jailbreak attacks on large language models (LLMs) reveal a mismatch in current guardrails: they operate on individual turns, while attacks unfold as trajectories across conversations. We propose a shift from content to dynamics, modeling conversations as paths in representation space and asking whether adversarial intent is encoded early in their geometry. We introduce PsychoPass, a framework that extracts geometric features from conversation trajectories in embedding space to predict a potential attack before harmful content is produced. These features achieve near-perfect performance in naïve classifiers, which is largely explained by the inclusion of number of turns as a feature. After removing this confound, a smaller but consistent geometric signal remains, with classification performance that does not depend meaningfully on encoder choice. Crucially, this signal appears early in the conversation: attack outcomes remain above chance from short prefixes alone, more reliably than baseline guardrails. A supporting theoretical analysis explains these findings via a decomposition of length and shape, a detection bound based on prefix length, and encoder invariance. Together, these results show that adversarial conversations leave an early, representation-robust geometric fingerprint suitable for online monitoring.

Muberra Ozmen, Subhabrata Majumdar

Coveo · Indian Institute of Management Bangalore

Adversarial Attacks on LLMs LLM Safety Jailbreak Defense

Jun 1, 2026cs.CR

MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models

Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs. Because mask tokens are native inputs and tokens are committed by confidence rather than position, harmful content can be induced through infilling and outside the monitored prefix. Existing jailbreaks either miss this native infill capability or rely on low-diversity mask-bearing templates applied uniformly across goals, with little structural adaptation or accumulated attack experience. We propose MaskForge, a fully black-box adaptive attack that casts dLLM red-teaming as optimized search over a growing library of structural patterns. MaskForge abstracts successful attempts into reusable schemas, selects goal-compatible patterns with a UCB bandit, and invokes a scorer-guided fallback when the current library fails. Successful attempts are distilled back into the pattern library, enabling experience to accumulate across goals. Across five public dLLMs and three benchmarks, MaskForge achieves an average attack success rate of 79.3%, a 17.6% relative improvement over the strongest competing dLLM baseline. The matured pattern library further transfers to AdvBench without any updates, achieving a 88.2% attack success rate and a 67% relative improvement over the strongest competing baseline.

Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu +3

University of Wisconsin-Madison · Johns Hopkins University · Responsible AI Research (RAIR) Centre, The University of Adelaide +1

Masked Diffusion Models Adversarial Attacks on LLMs LLM Safety Black-Box Adversarial Attacks Diffusion Language Models

Jun 1, 2026cs.CR

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents

Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents to manage. We study two complementary directions for this threat. First, we evaluate guardian-based defenses: an intermediary LLM agent that acts as a mediator for skill file access (dynamic guardian) or pre-rewrites these files at build time (static guardian). Across three LLM agent families, our guardians cut attack success rate (ASR) by well over half while preserving task utility. Second, we stress test them through attack reframing using four attacks that preserve the malicious instruction but change the phrasing. For non-guardian setup, the reframing pushes the ASR up to 81.4%, but the dynamic guardian brings it down to 18.6%, showing that real-time mediation is a robust defense.

Yoshinari Fujinuma, Varun Gangal, Traian Rebedea +4

Patronus AI · NVIDIA

Adversarial Attacks on LLMs LLM Agent Security Adversarial Robustness of Language Models LLM Agent Safety

May 31, 2026cs.AI

Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts

Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve intent while triggering commonsense hallucinations. This vulnerability is urgent, as LLMs are rapidly integrated into safety-critical domains where factual reliability is non-negotiable. Existing attack methods either lack efficiency or fail to capture the adaptive strategies of real-world adversaries. We propose an A*-inspired Factual Error Induction Framework, a framework for generating semantically aligned yet obfuscated prompts. At its core is a Hierarchical Rewrite Strategy guided by a dynamic semantic dispersion coefficient

γ

that balances conservative edits early with aggressive obfuscations later, following a reverse simulated annealing schedule. To enhance interpretability, we further introduce Agentic Mechanism Labeling, which discovers and refines adversarial mechanisms, offering interpretable reverse optimization. Theoretically, we prove that prompt rewriting follows a contractive recurrence, leading to semantic collapse as

γ

decreases. Empirically, across diverse LLMs, our method achieves higher attack success rates than exhaustive exploration while requiring fewer attempts, demonstrating both efficiency and effectiveness.

Boxuan Wang, Zhuoyun Li, Xiaowei Huang +1

University of Liverpool Merseyside, United Kingdom

Adversarial Prompt Generation Adversarial Attacks Adversarial Attacks on LLMs

May 31, 2026cs.CR

Inference Cost Attacks for Retrieval-Augmented Large Language Models

Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources. This high operational cost exposes a critical vulnerability to Inference Cost Attacks (ICAs). However, existing ICAs often rely on the impractical assumption of direct prompt manipulation. We argue that a more feasible and potent threat to RAG-enhanced LLM systems arises from poisoning external knowledge bases (e.g., web knowledge from the Internet). In this work, we introduce the Retrieval-Augmented Inference Cost Attack (RA-ICA), a novel attacking paradigm that targets the computational cost of RAG-enhanced LLM systems by injecting malicious documents into external knowledge corpus. To operationalize this attack, we propose Computational Resource Exhaustion via External Poisoning (CREEP), a novel framework that leverages LLM agents to automatically craft malicious documents that are both semantically relevant for retrieval and potent for inducing an abnormal increase in token consumption during the inference phase. To enhance the attack's effectiveness, we introduce Memory-Augmented Group Relative Policy Optimization (MA-GRPO), a novel reinforcement learning algorithm that fine-tunes the agents by learning from a dynamic memory of historical best adversarial documents. Extensive experiments across three real-world datasets demonstrate that RA-ICA increases token consumption by up to 13.12 times with an over 90% success rate, without degrading the integrity of the generated answer.

Chengliang Liu, Liangbo Ning, Yujuan Ding +1

The Hong Kong Polytechnic University Hong Kong, Hong Kong

Retrieval-Augmented Generation Adversarial Attacks RAG Poisoning Attacks Adversarial Attacks on LLMs RAG Security

May 30, 2026cs.AI

Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

LLM agents increasingly act after consuming ranked external information streams such as social feeds, search results, retrieval contexts, and email queues, yet safety evaluations almost always test the model or the user prompt in isolation, never the upstream ranker that decides what the agent reads just before it acts. We introduce a controlled protocol that holds the model, persona, topic, and final decision prompt fixed and varies only the composition and ordering of the posts an agent encounters during a preceding ten-turn "scrolling" phase, isolating the causal effect of feed curation on a downstream decision. Across 2,785 decision rollouts on four modern open instruct LLMs from three independent labs, we identify three response regimes: adversarial capitulation, default saturation, and a default-direction asymmetry in which a one-sided feed tips a decision the model was genuinely uncertain about (in the clearest cases from 5% to 100%; Fisher p as low as 3 x 10^-10) but cannot dislodge one it already favors or holds firmly. The effect follows a dose-response curve, survives a generator swap that rules out a writing-style artifact, generalizes across several decision domains including security-relevant choices such as removing a deployment approval gate or relaxing access controls, and is partly mitigated by two simple feed-level defenses; a frontier model retains its default. We characterize the recommender as a practical, default-bounded control surface for LLM agents, and argue that agent evaluations must audit the feed layer rather than the final prompt alone.

Rana Muhammad Usman

Independent Researcher

Adversarial Attacks on LLMs LLM Agent Evaluation LLM Decision-Making LLM Agent Safety

May 30, 2026cs.CR

Cross-Generational Transfer of Adversarial Attacks Reveals Non-Monotonic Safety Alignment in LLMs

Safety alignment in LLMs does not improve monotonically across model generations. Studying four generations of Google's Gemma family (7B-31B) with quality-diversity evolution (MAP-Elites) as an automated red-teaming probe, we find that Gemma 3 (12B) exhibits 68.7% +/- 5.7% attack success rate (ASR; mean +/- std, 3 seeds), significantly higher than its predecessor Gemma 2 (45.5% +/- 7.2%; p = 0.030, paired bootstrap) and its successor Gemma 4 (33.9% +/- 1.8%). Replaying evolved attack archives across generations reveals that attacks from other generations transfer to Gemma 3 at 44-46% but only 14-18% to Gemma 4, indicating that Gemma 4's safety gains generalize beyond the attack distributions evolved against earlier generations. Under our 8B judge, copyright and cybercrime vulnerabilities register at near-100% across all generations, though a second-judge audit (Section 6) suggests the copyright result is sensitive to judge choice. Misinformation ASR jumps from 29% to 99% between Gemma 2 and Gemma 3 and remains elevated at 77% in Gemma 4, indicating the regression was not fully addressed. These patterns are invisible to static benchmarks and emerge only through adaptive, longitudinal probing. All experiments use 3 random seeds with a unified self-hosted judge; code and artifacts are available at https://github.com/bassrehab/red-queen.

Subhadip Mitra

Research Lead, Rota Labs

Adversarial Attacks on LLMs LLM Red Teaming LLM Safety Alignment LLM Safety Evaluation Transfer-Based Adversarial Attacks

May 30, 2026cs.CR

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish. We introduce a quality-diversity evolutionary framework that operates at the semantic level, evolving interpretable attack strategies rather than token sequences. Using MAP-Elites, we maintain a diverse archive of attacks across behavioral dimensions (strategy type, encoding method, prompt length). In experiments across GPT-4o-mini, Claude 3.5 Sonnet, Gemini 2.0 Flash, and an open-weight coding model (Devstral-small-2), we discover distinct vulnerability profiles: GPT-4o-mini is vulnerable to hypothetical and multi-turn framing combined with ROT13 encoding (fitness 0.8), Gemini to direct attacks with ROT13 and multi-turn with Leetspeak (0.8), while Claude shows uniformly ambiguous responses across all strategies (max 0.4). The semantic representation produces interpretable attacks that reveal systematic, model-specific weaknesses, providing actionable insights for improving LLM safety and a reproducible baseline for evaluating future frontier models. Code and experiment artifacts are released at https://github.com/bassrehab/red-queen.

Subhadip Mitra

Research Lead, Rota Labs

Adversarial Prompt Generation Adversarial Attacks on LLMs LLM Jailbreak Attacks LLM Safety Evaluation

May 30, 2026cs.CR

MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety

Patient-facing medical chatbots are commonly evaluated on single-turn prompts, yet real users push back after refusals, add urgency, and invoke authority. We introduce MultiTurnPSB, a four-turn adversarial extension of PatientSafetyBench, and evaluate GPT-4.1-mini under fixed template, template-adaptive, and live adversarial attacks. Unsafe responses rise from 35% to nearly 80% by Turn 4 under live attack. Under the same adversary, GPT-4.1-mini and Claude Sonnet 4.5 are statistically indistinguishable at baseline but diverge to a 19x gap by Turn 4, a difference invisible to single-turn evaluation. We characterize four degradation trajectory signatures and identify a two-element attack formula responsible for most catastrophic failures. A lightweight input-side classifier reduces Turn 4 unsafe responses by 52 percentage points despite severe accuracy degradation, but the 45% false alarm rate on benign queries is the primary deployment constraint. A methodological finding also emerges: Claude Sonnet refused to generate adversarial messages in over half of late-turn conversations despite explicit red team framing, suggesting safety training may generalize to the attacker role.

Anushka Sheoran, Yiduo Hao

University of Pennsylvania

Language Model Safety Evaluation Adversarial Attacks on LLMs Multi-Turn Jailbreak Attacks

May 30, 2026cs.LG

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type. Whether a model treats a malicious instruction the same way regardless of where it arrives has not been systematically studied. We introduce the Safety Asymmetry Score (SAS), which measures how much a model's susceptibility to adversarial content shifts depending on whether that content arrives in the user message, tool metadata, or tool output, using matched payload pairs that keep the malicious text identical and vary only the context of delivery. Evaluated across 6 production LLMs and three attack families, we find a consistent and informative asymmetry: agent-native models are substantially more vulnerable when adversarial content arrives via tool descriptions than via user messages, while general-purpose models show the reverse. This asymmetry further inverts when the same content is delivered through tool outputs rather than descriptions, suggesting models implicitly treat tool metadata as trusted instructions and tool results as ordinary data. A mechanistic study on Llama 3.3 70B reveals that the safety-relevant representation is causally present at mid-to-late network depths but non-linearly encoded, explaining why linear probes fail to detect it. These findings expose a systematic, channel-dependent blind spot in how current tool-using models handle adversarial content.

Mohammed Sameer Syed, Rozhin Yasaei

University of Arizona

Adversarial Attacks on LLMs Prompt Injection Attacks LLM Safety Evaluation LLM Agent Safety

May 29, 2026cs.CR

EvoDefense: Co-Evolving Black-Box Defense with Large Language Models

Large Language Models (LLMs) remain highly vulnerable to diverse attacks, particularly in black-box settings where the internals of target models are inaccessible. Existing black-box defenses typically rely on pre-defined filtering heuristics, which often fail to generalize to unseen attack types and target model architectures. We introduce EvoDefense, an experience-guided co-evolving black-box defense paradigm. EvoDefense employs a guard LLM to detect malicious queries and an experience memory module to accumulate defense knowledge from previous interactions. At the core of EvoDefense is a continuous attack-defense evolution loop, where an attack generator and the guard model iteratively refine their attack strategies and defense policies through experience-guided optimization. This design enables EvoDefense to generalize across unseen attacks and target models without retraining. Experiments on HarmBench, AdvBench, and AlpacaEval show that EvoDefense achieves consistently strong defense performance across seven popular models and five representative LLM attacks, while preserving competitive general capabilities. On HarmBench, EvoDefense reduces the attack success rate (ASR) of AutoDAN-turbo on Gemini-3-flash and LLaMA-3-8B-Instruct from 29.4% and 43.4% to 8.4% and 6.2%, respectively.

Yu Li, Yuenan Hou, Yingmei Wei +2

National University of Defense Technology · Shanghai AI Laboratory

Evolutionary Optimization Adversarial Attacks on LLMs LLM Safety Black-Box Adversarial Attacks Jailbreak Defense

May 29, 2026cs.CR

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of conversation and the user's instructions. In this paper, we propose Persona Attack, a memory injection based jailbreak method that manipulates the model's context window through a step by step approach. Experimental results from applying Persona Attack to several widely used LLMs reveal that, as injections accumulate in memory, models increasingly prioritize these instructions over their internal safety alignment mechanisms. Furthermore, our experiments empirically demonstrate that the attack success rate varies not only according to the memory implementation of the model, but also combinations of instructions and can reach 95% under specific instruction configurations.

Junyoung Park, Seongyong Ju, Sunghwan Park +1

Chung-Ang University

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

May 28, 2026cs.CL

Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs

Large language models must frequently process untrusted inputs, such as judging an answer from another model or running tasks like spam and harm classifiers while under adversarial pressure. These inputs are often string-formatted directly into a prompt template, leaving systems fragile to manipulation. Current LLM specs from major providers like OpenAI distinguish trustworthiness along an Instruction Hierarchy, from System messages (most trusted) to Tool Results (least trusted). A possible natural mitigation is to wrap untrusted content in a mock tool call as a quarantine. We explore this hypothesis with an automated redteaming search over static attack strings across seven models and three LLM-as-a-Judge tasks. Counter to our hypothesis, tool-wrapping does not broadly improve robustness. On a binary evaluation task (GSM8K grading) it typically increases attack success rates, an apparent inversion of the instruction hierarchy. On scalar and pairwise tasks the effect is smaller and model-dependent, with no tested model reliably helped, and several showing inversion. We recommend evaluating this limitation in deployed systems, and longer-term, pursuing stronger Instruction Hierarchy training or new untrusted-input primitives.

David Gros, Adam Gleave

Language Model Safety Evaluation Adversarial Attacks on LLMs LLM Security LLM Reliability Prompt Injection Defense Language Model Robustness

May 28, 2026cs.CR

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the security of that code becomes critical. Prior work has shown that minor prompt perturbations degrade the functional correctness of LLM-generated code, but whether they also compromise code security has remained unstudied. We apply token-level mutations to prompts across three models and five programming languages, and show that mutations as small as a single-character change can flip generated code from secure to vulnerable. Probing the models' hidden states reveals that this fragility is partially encoded in prompt representations, but unevenly so. Input-handling vulnerabilities, where the model omits validation or sanitization, are more predictable (mean AUC 0.753) than secure-defaults vulnerabilities, where insecure code stems from one local choice such as a weak algorithm or unsafe parameter (mean AUC 0.674). These results show that the threat model for LLM-assisted coding extends beyond prompt injection to ordinary prompt variation, and indicate that input-handling flaws can be caught before generation while secure-defaults flaws require intervention during decoding.

Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic

IEM, HES-SO, Le Foyer, Techno-Pôle 1, Sierre, Switzerland · Cyber-Defence Campus, armasuisse Science and Technology, Thun, Switzerland

Prompt Sensitivity Adversarial Attacks on LLMs Secure Code Generation

May 28, 2026cs.CL

Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese

When Large Language Models (LLMs) are deployed in Chinese-language settings, a troubling pattern emerges: safety systems that work well in English break down. These systems struggle to cross linguistic and cultural bound-aries, leaving models exposed to adversarial prompts that exploit Chinese-specific evasion techniques, including Pinyin romanization, character decomposition, internet slang, and hedging tone. To address this gap, we introduce ChiSafe-PAS (Chinese Safety Pilot Annotation Set), a human-annotated benchmark of 1,897 adversarial Chinese prompts spanning four high-stakes domains: self-harm and violence, drug and illicit trade, fraud, and satire. Of these, 1,544 entries carry complete gold-standard annotations: a 3-class response label (REFUSE, SAFE-REDIRECT, RESPOND), a nine-category obfuscation taxonomy, a risk-level rating, and annotator rationale. We describe the dataset design, annotation process, and obfuscation taxonomy in detail. Our primary goal is practical: to give the research community a high-quality, culturally grounded resource for benchmarking LLM safety alignment. In doing so, we engage three broader tensions in the field: the blurring boundary between training and evaluation data, the need for domain coverage grounded in real-world risk, and the limits of scale as a substitute for cultural expertise.

Wajdi Zaghouani, Kholoud K. Aldous, Yicheng Gao

Northwestern University in Qatar

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

May 28, 2026cs.CR

SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing

Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We introduce SciIntBench, an adversarial benchmark of 810 prompts across ten RCR categories and three scientific domains. Each scenario appears as an Overt Adversarial, Covert Adversarial, and Benign version, allowing us to jointly measure framing-sensitive refusal of misconduct and helpfulness on legitimate requests. We evaluate 16 commercial and open-weight LLMs from six providers (2024--2026), producing 12,960 responses. We find that scientific integrity alignment is strongly framing-sensitive: models refuse explicit misconduct far more reliably than covert violations, especially failing when misconduct is presented as a pressure-driven shortcut. Refusals vary by RCR category, with weaker boundaries around transparency, plagiarism, and fabrication.

Almene De Meran Meguimtsop, Maria Leonor Pacheco, Daniel E. Acuna

Department of Computer Science, University of Colorado Boulder, Boulder, CO 80309

AI for Science Adversarial Attacks on LLMs LLM Refusal Behavior LLM Safety Evaluation

May 28, 2026cs.CR

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills

LLM-powered coding agents increasingly participate in software development workflows by generating code, selecting dependencies, and producing package installation commands. This creates a new software supply chain risk: when an agent hallucinates a non-existent package, an attacker may register the hallucinated name and later compromise users who install it. Existing package hallucination attacks and defenses primarily focus on naturally occurring hallucinations, targeted dependency steering, or post-hoc package validation. In this paper, we introduce \emph{Neutral Prompting Attack} (NPA), a highly stealthy attack paradigm in which semantically benign instructions, such as encouraging imagination and exhaustiveness, increase package hallucination propensity without containing explicit malicious intent. Unlike targeted dependency steering, NPA does not specify an attacker-chosen package. Instead, it shifts the model's dependency generation behavior toward more speculative package names. We evaluate NPA across multiple coding-oriented LLMs and package hallucination benchmarks. Our results show that NPA increases both \emph{Hallucination ASR} and \emph{Pip Install ASR}, changes the distribution of hallucinated package names, and evades existing static-analysis, LLM-based, and agent-based Skill defenses. These findings reveal that harmless-looking prompts can covertly manipulate hallucination behavior and create downstream software supply chain risks.

Chia-Yi Hsu, Chia-Mu Yu, Chun-Ying Huang +1

Department of Computer Science National Yang Ming Chiao Tung University · Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University · School of Computing Institute of Science Tokyo

Adversarial Prompt Generation AI Coding Agents Adversarial Attacks Hallucination in Language Models Adversarial Attacks on LLMs Software Supply Chain Security

May 27, 2026cs.AI

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly decodable well before the final layer, indicating that safety-relevant behavior is represented in intermediate activations before output generation. To test whether this signal is actionable, we introduce Mechanistic AutoDAN, a probe-guided variant of AutoDAN that replaces full-model fitness evaluation with partial forward passes and probe-based scoring inside a genetic prompt search loop. Across the evaluated models, our method achieves attack success rates competitive with vanilla AutoDAN while reducing per-iteration search time by up to 72%, and probe-guided prompts match or exceed AutoDAN's cross-model transfer in several configurations. We further find that the usefulness of probe guidance increases with model scale. Our results suggest that refusal-relevant information is decodable from intermediate activations and can serve as an effective search signal in an AutoDAN-style discrete jailbreak optimization loop, especially for larger and more robust models.

Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta +4

University of Padua, Italy · 2Örebro University, Sweden · 3Fondazione Bruno Kessler, Italy

LLM Interpretability Adversarial Attacks on LLMs LLM Refusal Behavior LLM Jailbreak Attacks Refusal Behavior in Language Models Language Model Probing

May 27, 2026cs.CR

Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems

Latent-based multi-agent systems replace parts of explicit inter-agent communication with hidden representations, offering a new direction for efficient and flexible agent collaboration. However, moving coordination into latent space may also move attacks beyond the reach of visible-text inspection. In this paper, we study whether latent states can carry attack-associated information that remains effective during clean executions. To examine this question, we introduce a latent attack framework that reactivates attack-induced effects through latent interventions without reusing adversarial text. Extensive experiments show that the resulting latent-only attacks can substantially degrade task performance in clean executions, especially when applied to inter-agent KV-cache handoffs rather than local hidden states. Further control analyses indicate that this degradation cannot be reduced to arbitrary perturbations or invalid generation. Overall, our findings suggest that latent-based collaboration does not remove attack risk. It shifts part of the risk into less observable execution states, calling for safeguards beyond visible-text inspection.

Chenxi Wang, Ruiyang Huang, Jiayan Sun +2

Southeast University, Nanjing, China · Peking University, Beijing, China

Multi-Agent LLM Systems Adversarial Attacks Adversarial Attacks on LLMs AI Agent Security Multi-Agent Communication

May 26, 2026cs.CR

HARP: Measuring Harm Amplification in Multi-Agent LLM Systems

Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability, but creates a propagation risk: a bounded perturbation to one component can be reused by other agents and amplified into system-level harm. We introduce HARP (Harm Amplification through Role Perturbation), a trace-first methodology for studying local-to-global harm amplification in multi-agent LLM systems. HARP compares paired clean and perturbed executions and records specialist outputs, tool calls, memory reads/writes, guard events, oracle logs, latency, token cost, and decisions. We define local harm as deviation from targeted agents or corrupted channels, global harm as deviation over the full trace, and harm amplification as (H_global/H_local). This complements attack success rate with a measure of how strongly orchestration spreads harm beyond the attack point. We instantiate HARP in a finance-oriented seven-agent system with a deterministic decision gate and configurable attack harness for specialist compromise, collusion, shared-context corruption, and temporal or memory-persistent attacks. Across five defenses, prompt-only defenses preserve benign utility but leave high success and stealth; pre-tool and step-level guards reduce some failures with utility or latency costs; and IntegrityGuard, a trace-consistency defense, achieves the lowest attack success and global harm but introduces utility/cost trade-offs. Results show that single-specialist compromise produces the strongest amplification, shared-context corruption yields the highest attack success, and temporal persistence produces the largest malicious impact. HARP argues that secure multi-agent evaluation must measure not only bypass, but propagation.

Md Hafizur Rahman, Zafaryab Haider, Tanzim Mahfuz +1

Electrical and Computer Engineering University of Maine, ME, USA

Multi-Agent LLM Systems Adversarial Attacks on LLMs AI Agent Security Multi-Agent System Security

May 26, 2026cs.CR

Cordyceps: Covert Control Attacks on LLMs via Data Poisoning

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization, or online monitoring can neutralize. In this paper, we propose a data poisoning method that teaches an LLM an information hiding scheme reliably and stealthily through semantic associations between shared knowledge such as facts or concepts and attacker-chosen phrases. The induced hiding scheme can encode and decode arbitrary malicious instructions, thus revealing a new and subtle poisoning-induced vulnerability: covert control attacks. We precisely characterize covert control attacks and evaluate them across

5

LLMs,

3

backdoor defenses, and

4

prompt injection defenses. With a small poisoned fraction, covert control attacks outperform heuristic-based prompt injection attacks in average attack success rate by about

40\%

relative to clean fine-tuned models. They also circumvent defenses based on detection and fine-tuning, maintaining up to

93\%

attack success rate after backdoor defenses and up to

98\%

after prompt injection defenses.

Zedian Shao, Charles Fleming, Teodora Baluta

Georgia Institute of Technology · Cisco Systems

LLM Backdoor Attacks Adversarial Attacks on LLMs Data Contamination in Language Models

May 26, 2026cs.LG

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by jailbreaking the model. Yet, pretrained LLMs already encode substantial harmful knowledge across many domains, which raises an important question: can an adversary jailbreak safeguarded models, to achieve harmful usage without fine-tuning at all? In this paper, we show that open-weight safeguards are susceptible to simpler strategies that, despite being well known, have not been systematically evaluated against these safeguards. Specifically, we evaluate two low-cost attacks--abliteration and prefilling--that do not rely on gradient-based optimization. Across three harmfulness evaluation benchmarks (BeaverTails, HarmBench, and AdvBench), these attacks increase attack success rates against safeguarded open-weight models from below 10% to a range of 16%-96%. To mitigate this vulnerability, we introduce abliteration-resistant tuning (ART), which incorporates an abliteration-based objective into training. ART can be layered onto existing defenses and reduces the success rates of abliteration, prefilling, and their combination by 10%-20%. These findings indicate that the attack surface for open-weight models is broader than previously characterized, and that evaluations of safeguarding defenses should incorporate a more diverse set of attack strategies beyond adversarial fine-tuning.

Kevin Kuo, Virginia Smith, Chhavi Yadav

Carnegie Mellon University · Simons Institute, UC Berkeley

LLM Fine-Tuning Adversarial Attacks on LLMs Open-Weight Language Models LLM Safety LLM Jailbreak Attacks

May 25, 2026cs.CL

LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers

Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to adversarial attacks remain poorly understood. We present a systematic benchmark of LLM-as-a-Reviewer on 898 papers stratified from NeurIPS and ICLR, evaluating 12 LLMs along three axes: rating calibration, divergence from human reviewers, and resistance to prompt injection embedded via an invisible font-mapping attack. We find that LLMs systematically overrate weaker submissions and diverge from humans in topical emphasis, under-flagging Clarity and over-flagging Reproducibility, while producing reviews two to three times longer with lower lexical diversity and a more standardized vocabulary. Prompt injection remains highly effective. Simple hidden instructions can promote low-scoring papers to acceptance-level ratings in a substantial fraction of cases, with effectiveness varying sharply across model families. While LLMs offer utility in structuring evaluations, their integration into peer review requires safeguards against both intrinsic biases and adversarial risks.

Lingyao Li, Junjie Xiong, Changjia Zhu +5

University of South Florida · Missouri University of Science and Technology · University of Alabama +3

LLM Evaluation LLM-as-a-Judge Adversarial Attacks on LLMs LLM Reliability Language Model Bias Evaluation Automated Peer Review

May 25, 2026cs.CR

Evo-Attacker: Memory-Augmented Reinforcement Learning for Long-Horizon Tool Attacks on LLM-MAS

While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating specialized agents and external tools, the implicit trust in tool outputs creates a critical attack surface. Existing tool attacks are limited by domain specificity or fixed and static templates. To address these challenges, we propose Evo-Attacker, which formulates the tool attack as a self-evolving, memory-augmented reinforcement learning process. Evo-Attacker constructs a dynamic attack memory and employs deliberative reasoning to retrieve adversarial patterns and strategize modifying interventions at critical moments. Furthermore, we introduce Attack-Flow GRPO to optimize intermediate reasoning steps via terminal outcomes, addressing the long-horizon credit assignment challenge. Comprehensive experiments demonstrate that Evo-Attacker consistently outperforms baselines, highlighting its generalization and evolutionary capabilities and the urgent need for defensive tool safeguards.

Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4

1Beihang University · 2Beijing University of Posts and Telecommunications · 3China Academy of Information and Communications Technology

Adversarial Attacks on LLMs LLM Agent Security Multi-Agent System Security RL for LLM Agents

May 24, 2026cs.AI

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications

The widespread integration of Large Language Models (LLMs) necessitates rigorous and systematic safety evaluation. Existing paradigms either rely on constructed benchmarks to assess safety from predefined perspectives, or employ dynamic red-teaming to probe potential vulnerabilities. While effective, these approaches face challenges, as they depend heavily on expert domain knowledge, offer limited systematic guarantees, and are vulnerable to rapid obsolescence. To address these limitations, we introduce a novel framework POLARIS that brings the rigor of specification-based software testing to AI safety. POLARIS first compiles unstructured natural-language policies into First-Order Logic (FOL) representations, establishing a traceable link between high-level rules and concrete test cases. This formalization enables the construction of a Semantic Policy Graph, where complex policy violation scenarios are encoded as traversable paths. By systematically exploring this graph, POLARIS uncovers compositional violation patterns, which are then instantiated into executable natural-language test queries, enabling coverage-driven and reproducible safety testing. Experiments demonstrate that POLARIS achieves higher policy coverage and attack success counts compared to established baselines. Crucially, by bridging formal methods and AI safety, POLARIS provides a principled, automated approach to ensuring LLMs adhere to safety-critical policies with verifiable traceability. We release our code at https://github.com/huac-lxy/POLARIS.

Xiaoyue Lu, Xianglin Yang, Haijun Liu +4

Shenzhen Campus of Sun Yat-sen University, Shenzhen, China · National University of Singapore, Singapore · Independent Researcher

Automated Software Testing Language Model Safety Evaluation Adversarial Attacks on LLMs LLM Safety AI Safety

May 24, 2026cs.CR

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

The known stylistic biases in LLM judges, such as a preference for verbosity or specific sentence structures, present an underexplored security vulnerability. In this work, we introduce BITE (BIas exploraTion and Exploitation), a black-box adversarial framework that learns semantics-preserving edits to mislead an LLM judge and artificially inflate the scores it assigns. We cast the selection of stylistic edits as a contextual bandit problem and use a LinUCB policy to adaptively choose edits that maximize the judge's score without access to model parameters or gradients. Empirically, we test BITE across a diverse range of LLM judges and tasks, including both pointwise and pairwise comparisons on chatbot leaderboards and AI-reviewer benchmarks. BITE achieves an attack success rate exceeding 65% and raises scores by 1-2 points on a 9-point scale, all while preserving semantic equivalence. We further assess the attack's stealthiness, showing that BITE evades standard style-control methods and several detection baselines. Our findings expose a fundamental weakness in the LLM-as-a-judge paradigm and motivate robust, attack-aware evaluation. Our code is available at https://github.com/xianglinyang/llm-as-a-judge-attack.

Xianglin Yang, Bryan Hooi, Gelei Deng +2

School of Computing, National University of Singapore, Singapore · Nanyang Technological University, Singapore

LLM Evaluation LLM-as-a-Judge Adversarial Attacks on LLMs Bias in LLM-as-a-Judge Adversarial Text Attacks

May 23, 2026cs.AI

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new security risks, making them particularly vulnerable to jailbreak attacks. Existing approaches often rely on static CoT templates to elicit harmful outputs, but such fixed designs suffer from limited diversity, adaptability, and effectiveness. To overcome these limitations, we propose an adaptive evolutionary CoT jailbreak framework, called AE-CoT. Specifically, the method first rewrites harmful goals into mild prompts with teacher role-play and decomposes them into semantically coherent reasoning fragments to construct a pool of CoT jailbreak candidates. Then, within a structured representation space, we perform multi-generation evolutionary search, where candidate diversity is expanded through fragment-level crossover and a mutation strategy with an adaptive mutation-rate control mechanism. An independent scoring model provides graded harmfulness evaluations, and high-scoring candidates are further enhanced with a harmful CoT template to induce more destructive generations. Extensive experiments across multiple models and datasets demonstrate the effectiveness of the proposed AE-CoT, consistently outperforming state-of-the-art jailbreak methods.

Jianan Li, Simeng Qin, Xiaojun Jia +5

Northeastern University · The University of Hong Kong, Hong Kong, China · BraneMatrix AI, China +7

Adversarial Attacks on LLMs LLM Jailbreak Attacks Large Reasoning Models