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

Sep 16, 2026cs.AI

Market Signal Injection: Adversarial Context Manipulation of LLM Pricing Agents

Large language model (LLM) pricing agents may respond to how market data is presented, even when its numerical values remain unchanged. We introduce market signal injection (MSI), an attack that manipulates numerical formatting, competitor ordering, or qualitative market commentary without issuing explicit instructions. We evaluate nine open-weight models in simulated Bertrand duopoly and triopoly markets and three proprietary models in duopoly markets. Sentiment-based attacks produce the largest behavioral shifts, which propagate to other firms and alter profits and consumer surplus. Susceptibility varies across model families, and larger models are not consistently more robust. Matched neutral-text controls and a rule-based agent support a framing-based account of these shifts under the fixed demand parameters of our simulation. Episode-held-out probes distinguish baseline from attacked activations in all eleven re-evaluated model--condition pairs: linear AUC is 1.00 and MLP AUC ranges from 0.93 to 0.99. This separability does not by itself identify harmful pricing decisions. Input canonicalization removes the tested sentiment attacks, while decision boundary anchoring, which combines prompt constraints with output projection, provides partial mitigation under the tested adaptive attacks. These results identify data presentation as an attack surface for LLM pricing agents and motivate defenses that account for interactions among agents.

Dohun Lee, Hyunwoo Park

Graduate School of Data Science, Seoul National University

Adversarial Attacks on LLMs AI Agent Security Adversarial Robustness of Language Models Multi-Agent LLMs

Sep 15, 2026cs.CL

Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs

Open-weight language models publish the strings their chat templates use to mark turns, roles and tool results, which the tokenizer maps back to the reserved identifiers the model obeys. Anyone who controls text in a prompt can therefore write a turn boundary indistinguishable from one the serving stack wrote. We audit 256 deployed chat tokenizers. All are forgeable, and the flag usually recommended as a fix leaves 56.6% forgeable because it misses the tool and reasoning markers agent systems rely on. We propose nameless tokenization, which leaves the control entries with a reserved identifier and no surface string, so the content encoder cannot emit one and message content reaches the model unaltered. Across five tokenizer families it reproduces the standard token stream exactly on attack-free data and lifts accuracy on a probe of delimiter-bearing text from 8.5% to 59.9%, where sanitizers lose it. Separating a delimiter's appearance from its identifier shows the identifier matters little against a bare task instruction, but carries most of a forged tool result and most of any forged turn once the system message tells the model to treat user content as data.

Kisu Yang, Yoonna Jang, Heuiseok Lim

1VAIV Company · 2Hanwha Aerospace · 3Korea University

Adversarial Attacks on LLMs LLM Security Prompt Injection Attacks

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.LG

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

Safety guardrails in open-weight language models can be readily bypassed using Refusal Feature Ablation (RFA), a technique that identifies and projects out a linear refusal direction from the residual stream, often achieving a high attack success rate (ASR) while preserving model capability. Defending against these attacks typically requires computationally expensive safety finetuning for every new checkpoint. We introduce Decoy Direction Optimization (DDO), a fast, post-hoc weight-editing defense that requires no base-model finetuning. Our approach is based on a simple mechanistic insight: ablation attacks rely on contrastive estimators to find the refusal direction. Rather than trying to hide the true refusal circuitry, DDO actively injects a high-magnitude, nonlinear decoy signal into the network's MLP neurons. When an attacker attempts to locate the refusal direction, the decoy corrupts their estimator, tricking them into ablating a harmless orthogonal feature while the actual safety mechanism remains intact. We prove a spectral bound formalizing this effect and evaluate DDO across six model families, achieving <10% ASR under standard RFA. On Llama-3-8B-Instruct, DDO remains comparable to trained defenses under adaptive multi-phase attacks (65% vs. 58% worst-case ASR) and reduces Heretic weight-level attack ASR from 88.7% to 18%, all at 30 to 450 times lower optimization cost per configuration than the trained baselines.

Aashiq Muhamed, Mona T. Diab, Virginia Smith

Carnegie Mellon University

Adversarial Attacks on LLMs LLM Safety Model Editing

Sep 14, 2026cs.CR

Universal Defenses for Tool-Integrated LLM Agents Against Adversarial Attacks

Large Language Model (LLM) agents have demonstrated impressive capabilities across a variety of domains, particularly when integrated with external tools for multi-step task completion. However, they are increasingly vulnerable to adversarial attacks, including direct prompt injection, indirect prompt injection, memory poisoning, and backdoor attacks, which exploit the model's openness to prompt injection and tool manipulation. In this work, we explore practical and generalizable defense strategies within a unified framework across these four attack types. We introduce two universal tool-based defenses: Attacker Tool Filtering, which uses anomaly detection (e.g., Isolation Forest) to identify and remove suspicious tools, and Normal Tool Recalling, a white-box method that restores the agent's original toolset prior to planning. Additionally, we incorporate prompt-based defenses: Chain-of-Thought prompting and self-reflection techniques to enhance reasoning and task paraphrasing to mitigate attacks. Experimental results across both four open-source LLMs (Gemma2-9B, Qwen2-7B, LLaMA3-8B, and LLaMA3.1-8B) and three proprietary LLMs (GPT-3.5, GPT-4, and GPT-5) show that our methods significantly reduce the Attack Success Rates (ASR), achieving 0% ASR in many settings, while preserving or even improving the original task success rate. These findings highlight the promise of simple, modular, multi-layered defenses for strengthening the security and robustness of tool-integrated LLM agents. The code is available at https://github.com/Xiaoyan-Lisa/Defenses-for-Tool-Integrated-LLM-Agents-Against-Adversarial-Attacks.

Xiaoyan Li, Yunli Wang

Department of Computer Science University of Toronto Toronto, Ontario, Canada · Digital Technologies Research Centre National Research Council Canada Ottawa, Ontario, Canada

Adversarial Attacks on LLMs Backdoor Defense in LLMs AI Agent Security Prompt Injection Attacks on AI Agents Tool Access Control for LLM Agents

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 14, 2026cs.AI

Overflip: Repetition-Induced Label Flips in Guardrail Models

Guardrail models are classifiers deployed to screen malicious prompts and responses in LLM-based services. To meet latency constraints, many lightweight guardrails adopt compact Transformer backbones (e.g., DeBERTa) that are trained with short context windows (typically 512 tokens) and rely on bucketed relative positional encodings to process longer inputs. Prior evaluations assume that a guardrail's decision is stable as the input is lengthened. We show that this assumption can fail. We identify Overflip, a repetition-induced instability where repeating a prompt causes the guardrail's prediction to flip (MAL

\to

BEN) as the sequence grows. We conduct experiments on 9 widely used lightweight guardrail models. Five exhibit MAL

\to

BEN flips on a benchmark of 100 prompts, with confidence margins shrinking steadily with repetition. Among these vulnerable models, flip rates range from 8% to 92%, with first flips occurring at roughly 2.6k--9.4k tokens. Our analysis suggests Overflip differs from traditional attention-dilution baselines, which aim to divert the model's attention away from tokens associated with malicious content, shifting it instead toward unrelated content, such as benign padding or shuffling. While Overflip preserves malicious content, it homogenizes token-level attention over repeated structure and induces a distinct, more gradual attention-dispersion trajectory than padding. Moreover, Overflip poses a greater threat to LLM services than traditional attention dilution methods. Because the bypassed prompt remains semantically intact and is still readily understood by downstream business LLMs, it can transmit malicious intent after passing the guardrail. These findings expose repetition as an attack surface for guardrail models and motivate length-robust evaluation and mitigation.

Xu He, Chih-Hsuan Lin, Hung-Mao Chen +3

1George Mason University · 2Virginia Tech · 3Missouri University of Science and Technology +1

LLM Guardrails Adversarial Attacks on LLMs LLM Security Language Model Robustness

Sep 10, 2026cs.CR

Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning

Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment bypasses that allow an adversarial user to elicit unwanted or harmful outputs from models. Arbitrary cipher, or covert communication, attacks are one such type of jailbreak and have previously been demonstrated against the fine-tuning APIs of commercial models. In these attacks, target models are trained on a corpus of encrypted harmful questions and responses and subsequently respond to harmful requests through the learned encryption scheme. In this paper, we show that newer frontier models do not require fine-tuning to acquire cipher-based communication skills. Instead, they can learn these skills through prompting and, when necessary, through in-context learning. Furthermore, model alignment is significantly weakened or entirely bypassed when communication occurs through the learned cipher. To the best of our knowledge, this constitutes a novel attack vector against commercial black-box large language models. We demonstrate successful jailbreaks against frontier models developed by Anthropic, Google, and OpenAI. Our attack bypasses commercial harmfulness classifiers because harmful content is encrypted and therefore appears as nonsensical text or gibberish.

Thomas Rivasseau

School of Information Studies McGill University

Adversarial Attacks on LLMs Jailbreak Attacks LLM Safety LLM Jailbreak Attacks

Sep 9, 2026cs.CL

Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning

Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative Steering injects undesirable-trait persona vectors during fine-tuning and removes them at evaluation time, yet the mechanism behind its lasting protection remains unclear. Analyzing its temporal optimization dynamics, we find that the defense emerges from an early compensatory adaptation phase followed by a steady-state phase where the corrective signal decays; in parameter space, attention output projections emerge as the dominant residual-write route for defensive updates. Through Intervention Delta Preservation (IDP) and IDP Continuation experiments, we further show that preserving or reinjecting the weight offset fails to maintain protection, indicating that preventative steering relies on active adaptation rather than a static defense. Motivated by this finding, we propose Progressive Intensity Scheduling (PIS), which starts with a moderate injection strength and increases it after static-strength alignment begins to decay. Across the evaluated Qwen2.5 and Gemma-3 models, PIS improves safety robustness over static-strength steering while reducing harmful trait expression.

Jing Guan, Yachao Yang, Zhaoliang Liu +3

JIUTIAN Research, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China

LLM Fine-Tuning Adversarial Attacks on LLMs Adversarial Robustness of Language Models

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.CR

How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE

Directional ablation removes an aligned language model's ability to refuse by projecting a single "refusal direction" out of the weights that write the residual stream. It needs no gradient-based training and no optimization, only a few hundred contrastive prompts, which makes it the canonical white-box attack on open-weight alignment. However, it has been established only on dense models up to roughly 70B parameters. We study whether it survives the shift to frontier mixture-of-experts (MoE) models whose residual streams are no longer a single tensor and whose weights ship quantized. We apply it to GLM-5.3-Flash (320B parameters, 288 routed experts, a four-wide hyper-connection residual, block-FP8). The attack survives the architecture, but what it reaches is no longer where a reader of the original recipe would look for it. Editing the attention, dense and routed-expert writers on their own removes 0.039, 0.016 and 0.148 of refusal respectively; editing all three together removes 0.776. As a result, 74% of the effect exists only under the joint intervention. The part the conventional recipe reaches by module-name matching accounts for 0.066 of that 0.776, which is why it fails silently on an MoE. The effect does not follow from removing just any direction: ablating a random direction orthogonal to it leaves refusal unchanged. A category-concentrated residue survives every edit we tried: subspaces fitted on violence, sexual content and hate leave measurable refusal at every rank from 1 to 12. We report the method, the 41-89 percentage-point reductions it achieves across seven harmful benchmarks with no detected change in capability, and the boundary where it stops.

Yi Shi, Tanyu Chen, Kai Shen

Continuum AI

Mixture-of-Experts Language Models LLM Alignment Adversarial Attacks on LLMs Refusal Behavior in Language Models

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 8, 2026cs.CR

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside model memory or rebuild deception at the protocol layer, leaving the serving tier unprotected and feeding nothing back into detection. HoneyRoute couples (i) a streaming router (a frozen 0.8B-embedding backbone with per-domain MLP heads), (ii) a dual-implementation honeypot (a rule/prompt-engineered code honeypot or a dedicated same-family replica), and (iii) an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus, the router reaches F1=.911 at 38 ms median added latency, matching 96% of a two-tier guard-LLM cascade's F1 at 1/385 of its latency with 0% evasion under 13 adversarial transformations; diverting the malicious share cuts production-model token consumption under concurrent flooding with real GCG-suffix payloads by 97.8%; the trained replica agrees with the production model on 92.9% of benign holdout requests, while naive unconditional bait injection collapses to 7.6% and selective camouflaged injection recovers to 88.9%, mapping the recoverable fidelity-traceability frontier; and a loop-trained correction head cuts misrouting of legitimate security research 9x while raising detection F1 to .933.

Han Jin

Independent Researcher

LLM Serving Adversarial Attacks on LLMs LLM Security LLM Routing

Sep 8, 2026cs.CR

ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing

Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built and tested in isolation, and the resulting scores are hard to trust. To tackle this, we present ACEA (Adversarial Co-Evolution Arena), a platform that connects a pluggable red-team adapter and a pluggable blue-team adapter to a shared target LLM and scores their attack and defense rates with an LLM judge. ACEA contributes four components. First, a pluggable, model-agnostic arena. Any red or blue project connects over a minimal HTTP protocol, which we call the ACEA Standard Adapter Protocol (ASAP). It can be written in any language, and a project that exposes nothing but the protocol is a full participant. Second, an evaluation methodology built for adversarial rounds. Seeding the target with canonical secrets gives verifiable ground truth that separates real leakage from hallucination. We also send each attack to the target even when the defense blocks it, which measures the attack's raw potency independently of whether it was stopped. Together these yield a per-round decomposition of attack strength and defense effectiveness. Third, a real-time, game-style visualization with a detailed end-of-battle report that localizes each failure. The evaluation thus becomes an actionable signal for improving a red or blue project. Fourth, an optional in-context improvement loop that turns each round's outcome into advisory hints for the next. An adapter can then adapt across rounds without keeping state, provided it reads the hints. We describe the design of ACEA and the metrics through which red and blue teams are scored head to head.

Yi Ting Shen, Kentaroh Toyoda, Alex Leung

Vulcan Research, AIFT Singapore

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

Sep 8, 2026cs.AI

Does Deeper Reasoning Compromise Alignment? Revealing and Mitigating of Alignment Collapse in Large Reasoning Models

The emergence of Chain-of-Thought (CoT) has established a robust foundation for Large Reasoning Models (LRMs). While deep reasoning is widely believed to enhance safety alignment, the stability of alignment mechanisms under extended reasoning remains underexplored. This paper challenges the prevailing view by revealing a critical vulnerability: Deep Reasoning May Induce Alignment Collapse. To rigorously quantify this phenomenon, we propose the Alignment Loss Rate (ALR) metric. Our experiments demonstrate that as reasoning depth increases, ALR rises significantly, indicating a severe degradation in model robustness against external perturbations. Capitalizing on this instability, a novel jailbreaking paradigm, Reasoning Trap (RT), is proposed. RT induces the model into extended reasoning to amplify the impact of adversarial attacks, leading to a sharp decline in safety capabilities. To elucidate the mechanism behind this collapse, we identify Attention Dilution as the root cause, arising from the competition for attention between the extended reasoning process and the original input. To mitigate this, Reasoning Residual Alignment (RRA), a lightweight defense strategy that dynamically re-emphasizes the input via residual connections integrated with the reasoning process.

Yu-Hang Wu, Yu-Jie Xiong, Henghua Zhang +3

Shanghai University of Engineering Science · The Hong Kong University of Science and Technology · A * STAR

Adversarial Attacks on LLMs Jailbreak Attacks LLM Safety Alignment Large Reasoning Models

Aug 26, 2026cs.LG

Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks

Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, reducing the risk of misuse. Recent work finds that refusal behavior in aligned language models can be mediated by a single activation direction or a low-dimensional refusal subspace shared across harmful prompts: ablating those directions suppresses refusals while largely preserves other model capabilities. Yet it remains unclear why safety-critical features in a wide range of models emerge in a concentrated, low-dimensional structure. In a case study of OLMo-2-0425-1B-Instruct we find that the refusal geometry reflects refusal training: activation updates resulting from refusal-completion first-token losses explain the resulting refusal direction and refusal subspace. We study refusal directions through the training dynamics across refusal datasets and reveal that their brittleness is associated with repetitive refusal starts, which in turn is linked to concentration of gradients and refusal features in a low-dimensional subspace. Across frozen-model analyses and controlled synthetic fine-tuning, we find evidence of a hardening lever: diverse refusal starts can raise stable ranks of gradients and activation changes, making refusals harder to remove with a vector ablation attack.

Andrey Labunets

UC San Diego

Adversarial Attacks on LLMs Adversarial Robustness of Language Models Refusal Behavior in Language Models

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 12, 2026cs.CR

Convergent Detour Hijacking: Task-Preserving Resource Amplification in Skill-Based LLM Agents

LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This progressive-disclosure design exposes two sequential control points to untrusted publishers: a static skill may steer an otherwise correct task onto an unnecessarily costly trajectory. Prior work studies selection manipulation, malicious skill instructions, and tool-chain resource amplification largely separately, leaving their end-to-end composition unclear. We introduce Convergent Detour Hijacking (CDH), a text-only, runtime-independent attack that couples these stages. Under shared semantic cover, a description establishes relevance during selection, while an aligned body reuses that rationale to fabricate plausible dependencies during planning. CDH attracts an attacker-controlled coordinator alongside legitimate skills, recruits unnecessary benign skills into a bounded detour, and then re-enters the original route to preserve task completion. We evaluate it across multiple LLM backends and 491 held-out tasks under single-task and multi-turn conditions. On DeepSeek-V4-Pro, the matched coordinator is selected in 80.02% of tasks; among coordinator-hit runs that complete tasks, token consumption and end-to-end execution time increase by 66.91% and 92.45%, respectively, while aggregate task completion remains comparable. Thus, correct outcomes do not guarantee trajectory integrity or cost safety.

Junliang Liu, Ruoyu Li, Wenxin Tang +4

School of Computer Science and Software Engineering, Shenzhen University · The Chinese University of Hong Kong · The Chinese University of Hong Kong, Shenzhen

Adversarial Attacks on LLMs LLM Agent Security LLM Agent Reliability

Aug 12, 2026cs.CL

Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs

Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior. Yet we show that this requirement is far from met: a single targeted persuasive argument is enough to collapse model accuracy to near zero, even when the argument is factually false. We formalize this threat as adversarial persuasion and introduce an adversarial reinforcement learning framework that trains persuader agents to change a target model's answer in a single interaction. First, we show that optimizing persuasion strategies through trial and error exposes vulnerabilities that static prompting misses: RL-trained persuaders raise persuasion success from approximately 24% to over 93% against the training-time persuadee. Second, we find that these learned strategies transfer to unseen models, achieving 83% attack success on Qwen-14B, 79% on Llama-3.1-8B, and 25% on GPT-4o-mini. Third, we demonstrate that a curriculum that bootstraps on more persuadable open-weight models before targeting harder models further increases GPT-4o-mini attack success from 25% to 38%. Moreover, our results reveal that optimized persuaders increasingly rely on credibility-based tactics, including fabricated citations and false authoritative evidence. Together, these findings expose a critical weakness in current LLM agents: even when they initially reason correctly, they can be steered toward false conclusions by optimized natural language influence. This positions persuasion robustness as a necessary safety criterion for multi-agent and human-AI decision-making systems.

Nimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur +1

University of Illinois Urbana-Champaign

Deception in Language Models Adversarial Attacks on LLMs Adversarial Robustness of Language Models Belief Updating in LLMs Persuasion in Language Models

Aug 11, 2026cs.SD

Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models

Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant computational overhead and resource consumption. While most existing denial-of-service (DoS) attacks target text-only LLMs, end-to-end (E2E) speech LLMs are rapidly emerging. Existing text-based DoS attacks primarily rely on prompt engineering, such as adversarial suffixes or semantic inducement, which exploit the discrete nature of text inputs and therefore cannot be directly transferred to continuous speech inputs. Moreover, prior studies on speech model security mainly focus on ASR or TTS systems, leaving the DoS vulnerability of E2E speech LLMs largely unexplored. To address this gap, we propose the perturbation-based DoS attack targeting E2E speech models. Instead of inducing long outputs through prompt manipulation, our method optimizes imperceptible acoustic perturbations to directly influence the model's autoregressive generation process while preserving the original input length. Specifically, we formulate the attack as a composite optimization objective that jointly suppresses EOS generation, encourages prolonged decoding, and largely preserves semantic consistency by integrating weighted EOS loss, top-k logit loss, length loss, and semantic alignment loss. To further improve stealthiness, we employ voice activity detection (VAD) to inject perturbations only into voiced regions. Extensive experiments on three open-source E2E speech LLMs demonstrate that our method achieves stable attack success rate while significantly increasing generation length and GPU resource consumption, revealing security risks in modern ALLMs.

Shuozhe Cheng, Kunlan Xiang, Mingxuan Li +3

Adversarial Attacks on LLMs Speech Language Models

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.CR

Stealing Reasoning Traces from Proprietary LLM APIs

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather than storing these traces server-side, providers return them to the client as blocks of encrypted text, which the client passes back with each subsequent request. Building on prior research, we identify an architectural vulnerability: these encrypted blocks are fully compatible and interchangeable across different sessions, users, and models within a provider's ecosystem. We exploit this compatibility to develop a scalable decryption jailbreak. By injecting an encrypted reasoning trace from a given model into a weaker, and less safeguarded model from the same provider, we force it to decode and output the trace verbatim in plaintext, without ever jailbreaking the more capable model directly. This vulnerability enables four distinct attack vectors. First, it circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as we demonstrate across Anthropic, OpenAI, and Google. Second, it allows for large-scale private data extraction. Developers frequently share session logs publicly, unaware of contents of the encrypted blocks. By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials. Third, it inadvertently reveals hazardous information hidden within the reasoning process, even in cases where the model's final, visible output safely rejects a malicious request. Fourth, attackers can leverage this flaw to execute invisible prompt injections, embedding malicious payloads entirely within encrypted blocks to poison public agentic rollouts. Following responsible disclosure, we propose concrete cryptographic and system-level mitigations to secure client-side reasoning.

Alexander Panfilov, David Schmotz, Ilia Shumailov +5

MATS Research · ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems +4

Model Extraction Attacks Adversarial Attacks Adversarial Attacks on LLMs Privacy Leakage in Language Models LLM Security Prompt Injection Attacks on LLMs

Aug 10, 2026cs.CL

Pragmatic Attack Surface: Vulnerabilities of Implicit Context in Large Language Models

In the era of large language models (LLMs), attackers often manipulate natural language to elicit unsafe or harmful outputs, creating a new natural language attack surface unique to LLM-based systems, where attacks directly exploit explicit linguistic cues in user prompts to bypass the safety mechanism of LLMs. However, such attacks can often be mitigated by existing safety alignment algorithms. On the other hand, human language is inherently grounded in pragmatics, necessitating typical context to interpret language, e.g., world knowledge, social norms. However, such contexts are often implicit because they are not directly expressed in human language and are not sufficiently leveraged in safety alignment, creating a fundamental mismatch between human language interpretation and safety alignment approaches. In this paper, we demonstrate that this mismatch exposes vulnerabilities in LLMs. We refer to this vulnerability as the pragmatic attack surface, which can be exploited to achieve high attack success rates. The experimental results demonstrate that our proposed approach outperforms baseline attack methods across various open-source and closed-source models by a substantial margin.

Bocheng Chen, Han Zi, Roucheng Ou +5

University of Mississippi · Indiana University Indianapolis · Michigan State University +1

Pragmatic Reasoning in Language Models Adversarial Attacks on LLMs LLM Safety

Aug 10, 2026cs.LG

Dual-Adversarial Safety Alignment: Cultivating Intrinsic Threat Comprehension in LRMs

Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs. Recent methods align LRMs using direct refusals or safety rationales, yet often focus on prompt patterns rather than intrinsic attack mechanisms. As a result, these pattern-centric alignments struggle to generalize across diverse jailbreaks, compromising adversarial robustness and reasoning utility. We propose AdvSafe, a dual-adversarial framework that enables LRMs to internalize unsafety knowledge by explicitly deconstructing adversarial mechanisms. This moves beyond pattern-dependent traces, fostering robust cognitive defense without compromising reasoning utility. Our pipeline operates via a two-phase adversarial game. First, in adversarial synthesis, an autonomous agent dynamically crafts deceptive jailbreak prompts, adapting its strategies to breach a strong teacher model. Second, in adversarial extraction, the breached teacher executes a cognitive counter-attack. For every successful jailbreak, the teacher unmasks the camouflage, explaining why the attack succeeds and how such prompts can be identified and mitigated. This dual-adversarial process yields a compact reasoning dataset capturing rich, generalizable unsafety knowledge. Student models trained on this dataset implicitly acquire safety alignment through intrinsic threat comprehension. Experiments show that with only 1K synthesized samples, AdvSafe-aligned LRMs achieve significantly stronger jailbreak robustness than existing baselines, with almost no utility degradation. Furthermore, AdvSafe improves robustness against out-of-distribution prompts, demonstrating that learning unsafety knowledge enables a superior robustness-utility trade-off and generalizes beyond seen attack patterns.

Hongli Shen, Shaopeng Fu, Qinbo Zhang +2

1King Abdullah University of Science and Technology · 2Stony Brook University

Adversarial Training Adversarial Attacks on LLMs LLM Safety Alignment LLM Security Adversarial Robustness of Language Models

Aug 9, 2026cs.LG

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.

Yu Ma, Hongli Shi, Jing Li +2

Google · University of New South Wales · University of Technology Sydney +2

LLM Safety Benchmarks Language Model Safety Evaluation Adversarial Attacks on LLMs Jailbreak Robustness Language Model Merging

Aug 8, 2026cs.CV

Forged Peer Judgments Mislead Multimodal LLM Judge Panels: Source-Blind Anchoring and Panel-Consensus Verification

Multimodal LLM judge panels can cross-reference peers, but a quoted peer judgment may itself be untrusted. We expose source-blind anchoring as a text-level attack surface in vision-language model (VLM) panels. Quoting independent visual judgments creates large anchoring gaps (19--26 percentage points) under both self and peer framing. A matched-content, label-only control changes the broken rate by only

-0.17

pp (95% CI

[-0.68,0.35]

), showing that the self/peer label itself does not explain the effect. Under our tested construction, deliberately generated, concise wrong quotes overturn originally-correct verdicts 1.5--2.7

\times

more often than naturally occurring wrong peer statements, with bootstrap 95% CIs excluding parity across two datasets and seven VLM judges. Because the two statement populations differ in selection and form, this ratio measures differential damage under the tested attack rather than a provenance-only causal effect. We then introduce panel-consensus verification, which cross-checks a quote against independently collected blind votes. It blocks 84.9% of fabricated attacks, cuts their net harm by 97.5%, and preserves the positive but statistically inconclusive point estimate for genuine peer information under leave-one-out re-verification. These results identify a low-cost attack surface and a concrete defense for safer multimodal collaborative evaluation.

Yang Shu

Zhejiang University, Hangzhou, China

LLM-as-a-Judge Adversarial Attacks on LLMs Vision-Language Model-as-a-Judge Multimodal Model Evaluation

Aug 7, 2026cs.LG

Diffusion LLMs as Targets and Adversaries: Mechanistic Safety Exploits

Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mechanisms remain poorly understood. In this work, we investigate DLLMs both as targets and as adversaries, exposing mechanistic vulnerabilities in diffusion-based alignment. We first show that safety alignment in DLLMs remains sparse and transferable across architectures. DLLMs initialized from autoregressive predecessors inherit the same mechanistic safety footprint as their source models, enabling transfer attacks via direct safety neuron mapping and pruning. Self-pruning increases attack success rates (ASR) from 2.6% to 73.8% on LLaDA and from 1.9% to 86.6% on Dream, while transfer pruning from Qwen2.5 increases ASR from 1.9% to 73.2% on Dream and from 7.0% to 86.3% on Fast-dLLM. Building on these findings, we introduce SN-Guided Diffusion, a fully offline black-box jailbreak framework that steers the diffusion process away from safety-triggering regions using a weighted safety neuron loss, which achieves near-perfect prompt separability (AUROC = 1.0 for benign-vs-jailbreak discrimination). Across multiple open and proprietary targets, our method achieves a transfer ASR of up to 77.1% on Llama-3-8B-Instruct, 86.9% on Qwen2.5-7B-Instruct, and 74.3% against Gemini-2.5-Flash-Lite, while requiring only 20 generation episodes per prompt. Compared to prior jailbreaking frameworks, our method achieves competitive transferability with orders-of-magnitude lower generation cost. Our codebase is available at https://github.com/ellyoana/sn-guided-diffusion.

Elena Dumitrescu, Gert Lek, Lydia Y. Chen +1

Delft University of Technology, Delft, The Netherlands · University of Neuchâtel, Neuchâtel, Switzerland.

Adversarial Attacks on LLMs LLM Safety Alignment Mechanistic Interpretability Transfer-Based Adversarial Attacks Diffusion Language Models

Aug 5, 2026cs.CL

Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment

Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep established safeguards. For instance, prior work by Andriushchenko et al. (2025) has found that changing the grammatical tense from present to past can be enough to elicit harmful responses. In this work, we uncover a more general failure of non-imperative syntactic forms. We demonstrate that this syntactic vulnerability exists in 16 models up to 70B parameters, using behavioral evaluation. To investigate the root cause, we apply causal mediation analysis, finding that refusal is partially conditioned on upstream syntactic features. By steering these purely syntactic features we are able to trigger and suppress refusal. Finally, we trace this ill-conditioning to linguistically biased post-training data of open-source models and show that increasing syntactic diversity can mitigate the issue. Our findings suggest that current alignment approaches introduce confounders that prevent a pure semantic grounding of the refusal decision.

Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1

University of Mannheim · Technical University Clausthal

Adversarial Attacks on LLMs LLM Safety Alignment Adversarial Robustness of Language Models Refusal Behavior in Language Models

Aug 5, 2026cs.LG

Sharding Prevents LLM Oversight Failures and Adversarial Exploitation

Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts, some decisions become weakly grounded in the evidence, even when that call receives the same token or tool budget as a panel of separate calls. Across expert-graded research replications, legal work, and clinical-trial assessments, agreement with experts falls as the number of verdicts per call grows. We identify sharding as the intervention that mitigates this failure in model-based oversight. Sharding partitions the requirements into smaller groups, assigns each group to a separate call, and aggregates the verdicts. Against a single call with the panel's full budget, sharding improves agreement while holding the model, evidence, total budget, and per-decision budget fixed. Overall, we find that a sharded weaker judge can outperform a more capable holistic judge and match that judge even when the latter receives the panel's full budget. Additionally, we find that sharding exhibits robustness against adversaries. A best-of-N adversary can hold the underlying work fixed, vary only its presentation, and increase an overloaded judge's acceptance of genuinely unmet criteria severalfold. Wherever sharding reduces baseline error, it removes this adversarial advantage, keeping over-acceptance low even as the adversary's search widens. Sharding does not address attacks that persuade the judge separately on each criterion rather than exploiting overload. In that setting, we find that debate-style opposition on top of sharding withstands such adaptive re-optimization.

Victor Akinwande, J. Zico Kolter, Aran Nayebi

School of Computer Science 2Neuroscience Institute Carnegie Mellon University

Scalable Oversight LLM Evaluation LLM-as-a-Judge Adversarial Attacks on LLMs Adversarial Robustness of Language Models

Aug 4, 2026cs.CL

Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks

Large language models (LLMs) are often used in conjunction with external knowledge sources to improve their factual accuracy and decrease hallucinations, through methods such as Retrieval-Augmented Generation (RAG). However, these systems remain susceptible to intrinsic hallucinations, where the model generates unfaithful or fabricated information that is not supported by the retrieved evidence. We propose a novel framework to assess model robustness against this phenomenon by stress-testing using natural, semantically equivalent variations of a user query found via adversarial optimization methods. We apply our framework, which enforces strict semantic equivalence constraints and an intrinsic hallucination objective, to a range of adversarial attack techniques across white-box, gray-box, and black-box adversarial settings. Evaluating these attacks on 5 open-source and 5 closed-source generator models across 3 datasets, we demonstrate that even state-of-the-art models are highly susceptible to meaning-preserving perturbations, which significantly degrade contextual faithfulness (by up to 50% for GPT-5-mini). Our findings indicate that faithful use of in-context evidence remains fragile even in state-of-the-art LLMs, motivating architectures and training objectives that enforce robust grounding independent of surface query form. Code is available at: https://github.com/atriviveksharma/intrinsic_hall

Atri Vivek Sharma, Brian Formento, Alessio Lomuscio

Imperial College London · Safe Intelligence

Retrieval-Augmented Generation Adversarial Attacks Hallucination in Language Models Adversarial Attacks on LLMs Adversarial Robustness of Language Models