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

Apr 18, 2026cs.CL

When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints

We identify and systematically characterize a class of task-structural alignment failures in large language models (LLMs): even when the harmful intent remains unchanged, changing the task presentation and output constraints can substantially alter model safety behavior. Specifically, when a harmful request is reformulated as a forced-choice multiple-choice question (MCQ) in which all options are harmful and no refusal option is provided, some models that refuse the equivalent open-ended query instead select, prefer, or justify a harmful option. We evaluate 14 proprietary and open-source models on a bilingual Chinese-English human-authored dataset covering five harm categories, together with 900 model-generated Chinese adversarial MCQs. On human-authored data, attack success rate (ASR) increases sharply as prompts shift from open-ended queries to explicit forced-choice formats, typically peaking under intermediate levels of choice constraint. Model-generated Chinese MCQs further weaken or eliminate the recovery regime observed on human-authored data, driving ASR close to saturation for multiple models. The observed transfer patterns are consistent with stronger generators producing more difficult or boundary-adjacent MCQs, although other properties of the generated inputs may also contribute. We also find that adding an explicit refusal option or a safety preamble substantially reduces ASR for several high-capability models, often to near-zero levels, although their effectiveness varies across target models. These findings suggest that safety evaluations centered on open-ended generation may underestimate risks in structured deployment settings, and that task structure should be treated as an important and diagnosable dimension of safety evaluation and alignment training.

Yuheng Chen, Zhiyu Wu, Bowen Cheng +2

Kagoshima University · Fudan University · China University of Petroleum-Beijing

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

Apr 17, 2026cs.CL

Stochasticity in Tokenisation Improves Robustness

The widespread adoption of large language models (LLMs) has increased concerns about their robustness. Vulnerabilities in perturbations of tokenisation of the input indicate that models trained with a deterministic canonical tokenisation can be brittle to adversarial attacks. Recent studies suggest that stochastic tokenisation can deliver internal representations that are less sensitive to perturbations. In this paper, we analyse how stochastic tokenisations affect robustness to adversarial attacks and random perturbations. We systematically study this over a range of learning regimes (pre-training, supervised fine-tuning, and in-context learning), data sets, and model architectures. We show that pre-training and fine-tuning with uniformly sampled stochastic tokenisations improve robustness to random and adversarial perturbations. Evaluating on uniformly sampled non-canonical tokenisations reduces the accuracy of a canonically trained Llama-1b model by 29.8%. We find that training with stochastic tokenisation preserves accuracy without increasing inference cost.

Sophie Steger, Rui Li, Sofiane Ennadir +4

Institute of Signal Processing and Speech Communication, Graz University of Technology, Graz, Austria · ELLIS Institute Finland & Aalto University, Espoo, Finland · King AI Labs, Microsoft Gaming +2

Adversarial Attacks on LLMs Neural Network Robustness Adversarial Robustness of Language Models Subword Tokenization

Apr 17, 2026cs.MA

Conjunctive Prompt Attacks in Multi-Agent LLM Systems

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We study \emph{conjunctive prompt attacks}, where a trigger key in the user query and a hidden adversarial template in one compromised remote agent each appear benign alone but activate harmful behavior when routing brings them together. We consider an attacker who changes neither model weights nor the client agent and instead controls only trigger placement and template insertion. Across star, chain, and DAG topologies, routing-aware optimization substantially increases attack success over non-optimized baselines while keeping false activations low. Existing defenses, including PromptGuard, Llama-Guard variants, and system-level controls such as tool restrictions, do not reliably stop the attack because no single component appears malicious in isolation. These results expose a structural vulnerability in agentic LLM pipelines and motivate defenses that reason over routing and cross-agent composition. Code is available at https://github.com/UCF-ML-Research/ConjunctiveAgents.

Nokimul Hasan Arif, Qian Lou, Mengxin Zheng

University of Central Florida, USA

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

Mar 11, 2026cs.LG

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed without injection to exponential growth with the number of inference-time samples. We first identify a minimal statistical mechanism for these two regimes by giving a small set of assumptions on the distribution of safe generation across contexts under which both scaling laws follow. To explain this phenomenon further, we propose a theoretical generative model of proxy language in terms of a spin-glass system operating in a replica-symmetry-breaking regime, where generations are drawn from the associated Gibbs measure and a subset of low-energy, size-biased clusters is designated unsafe. We analytically show how this model naturally realizes the minimal assumptions. Short injected prompts correspond to a weak magnetic field aligned towards unsafe cluster centers and yield a power-law scaling of attack success rate with the number of inference-time samples, while long injected prompts, i.e., strong magnetic field, yield exponential scaling. We observe qualitatively consistent behavior across a broad range of large language models, spanning parameter scales from 3B to 70B. In particular, the main trends remain stable across multiple attack methods, such as GCG and AutoDAN, as well as across benchmark datasets such as AdvBench and HarmBench.

Indranil Halder, Annesya Banerjee, Cengiz Pehlevan

John A. Paulson School of Engineering And Applied Sciences, Harvard University · Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology · Speech and Hearing Bioscience and Technology, Harvard Medical School +2

Adversarial Attacks on LLMs Prompt Injection Attacks on LLMs Language Model Scaling Laws

Feb 22, 2026cs.CL

Prompt Injection as Role Confusion

LLMs see the world as a single stream of text, partitioned into roles like <user> or <tool>. We trace prompt injection to role confusion: models perceive the source of text from how it sounds, not its labeled role. A command hidden in a webpage hijacks an agent simply because it sounds like <user> text, despite its <tool> label. We design role probes to measure how LLMs internally perceive "who is speaking," and find that injected text occupies the same representational space as the trusted role it imitates. We demonstrate this with CoT Forgery, a zero-shot attack that injects fabricated reasoning into user prompts and tool outputs. Models mistake the forgery for their own thoughts, yielding 60% attack success against frontier models with near-zero baselines. Strikingly, the degree of role confusion predicts attack success before a single token is generated. This mechanism generalizes beyond CoT Forgery to standard agent prompt injections, revealing prompt injection as a measurable consequence of role perception. To the model, sounding like a role is indistinguishable from being one. Project page and writeup: https://role-confusion.github.io

Charles Ye, Jasmine Cui, Dylan Hadfield-Menell

*Equal contribution 1Independent · 2Massachusetts Institute of Technology, Cambridge, MA, United States

Adversarial Attacks on LLMs Prompt Injection Attacks Prompt Injection Attacks on LLMs Prompt Injection Attacks on AI Agents

Feb 14, 2026cs.CR

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in this workflow, which we term Rubric-Induced Preference Drift (RIPD). Even when rubric edits pass benchmark validation, they can still produce systematic and directional shifts in a judge's preferences on target domains. Because rubrics serve as a high-level decision interface, such drift can emerge from seemingly natural, criterion-preserving edits and remain difficult to detect through aggregate benchmark metrics or limited spot-checking. We further show this vulnerability can be exploited through rubric-based preference attacks, in which benchmark-compliant rubric edits steer judgments away from a fixed human or trusted reference on target domains, systematically inducing RIPD and reducing target-domain accuracy up to 9.5% (helpfulness) and 27.9% (harmlessness). When these judgments are used to generate preference labels for downstream post-training, the induced bias propagates through alignment pipelines and becomes internalized in trained policies. This leads to persistent and systematic drift in model behavior. Overall, our findings highlight evaluation rubrics as a sensitive and manipulable control interface, revealing a system-level alignment risk that extends beyond evaluator reliability alone. The code is available at: https://github.com/ZDCSlab/Rubrics-as-an-Attack-Surface. Warning: Certain sections may contain potentially harmful content that may not be appropriate for all readers.

Ruomeng Ding, Yifei Pang, He Sun +3

University of North Carolina at Chapel Hill · 2Carnegie Mellon University · 3Yale University +1

LLM Alignment LLM-as-a-Judge Adversarial Attacks on LLMs Rubric-Based Evaluation Bias in LLM-as-a-Judge

Feb 8, 2026cs.CR

Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model

LLM inference is inherently expensive, even a modest slowdown can translate into substantial operating costs and severe availability risks. Recently, a growing body of research known as latency attacks focuses on crafting inputs to trigger worst-case output lengths. However, we report a contrary finding that these algorithmic-level latency attacks are largely ineffective against modern LLM serving systems. We reveal that system-level optimization such as continuous batching provides a logical isolation to mitigate contagious latency impact on co-located users. Thus, in this paper, we shift our focus from the algorithm to the system layer, and introduce a new Fill and Squeeze attack strategy targeting the state transition of the scheduler. Fill'' first exhausts the global KV cache to induce Head-of-Line blocking, while Squeeze'' forces the system into repetitive preemption. By manipulating output lengths using different attack prompts, and leveraging side-channel probing of memory status, we demonstrate that the attack can succeed in a practical black-box setting with much less cost. Extensive evaluations on vLLM indicate up to

75-742\times

TTFT degradation relative to benign baselines and

1.5-4\times

average slowdown on Time Per Output Token compared to existing attacks with 30-40% lower attack cost. Code: https://github.com/Phil-Fan/FS-attack

Tianyi Wang, Huawei Fan, Yuanchao Shu +2

Zhejiang University

LLM Security Adversarial Attacks on LLMs LLM Inference Serving LLM Inference Scheduling

Jan 29, 2026cs.AI

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs

Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction. However, this autonomy introduces a previously unrecognized security risk: agentic interaction fundamentally expands the LLM attack surface, enabling systematic probing and recovery of hidden system prompts that guide model behavior. We identify system prompt extraction as an emergent vulnerability intrinsic to code agents and present \textbf{\textsc{JustAsk}}, a self-evolving framework that autonomously discovers effective extraction strategies through interaction alone. Unlike prior prompt-engineering or dataset-based attacks, \textsc{JustAsk} requires no handcrafted prompts, labeled supervision, or privileged access beyond standard user interaction. It formulates extraction as an online exploration problem, using Upper Confidence Bound-based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration. These skills exploit imperfect system-instruction generalization and inherent tensions between helpfulness and safety. Evaluated on \textbf{41} black-box commercial models across multiple providers, \textsc{JustAsk} consistently achieves full or near-complete system prompt recovery, revealing recurring design- and architecture-level vulnerabilities. Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.

Xiang Zheng, Yutao Wu, Hanxun Huang +5

City University of Hong Kong · Deakin University · The University of Melbourne +3

Prompt Injection AI Coding Agents Adversarial Attacks on LLMs LLM Agent Security

Jan 19, 2026cs.CL

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement

Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written under the influence of alcohol, as a driver for safety failures in large language models (LLMs). We investigate three mechanisms for inducing drunk language in LLMs: persona-based prompting, causal fine-tuning, and reinforcement-based post-training. When evaluated on 5 LLMs, we observe a higher susceptibility to jailbreaking on JailbreakBench (even in the presence of defences) and privacy leaks on ConfAIde, where both benchmarks are in English, as compared to the base LLMs as well as previously reported approaches. Via a robust combination of manual evaluation and LLM-based evaluators and analysis of error categories, our findings highlight a correspondence between human-intoxicated behaviour, and anthropomorphism in LLMs induced with drunk language. The simplicity and efficiency of our drunk language inducement approaches position them as potential counters for LLM safety tuning, highlighting significant risks to LLM safety.

Anudeex Shetty, Aditya Joshi, Salil S. Kanhere

School of Computer Science and Engineering, UNSW Sydney, Australia · School of Computing and Information System, the University of Melbourne, Australia

Language Model Safety Evaluation Adversarial Attacks on LLMs Privacy Leakage in Language Models LLM Safety LLM Jailbreak Attacks

Jan 7, 2026cs.CL

Safety Is Not Universal: The Selective Safety Trap in LLM Alignment

Current safety evaluations of large language models (LLMs) create a dangerous illusion of universal protection by aggregating harms under generic categories such as "Identity Hate", obscuring vulnerabilities toward specific populations. In this work, we expose the Selective Safety Trap: a systemic failure mode where models robustly defend specific populations while leaving underrepresented communities highly vulnerable to identical adversarial attacks. To systematically audit this phenomenon, we introduce MiJaBench, a bilingual (English-Portuguese) adversarial benchmark comprising 43,961 controlled jailbreaking prompts across 16 minority groups. By evaluating 14 state-of-the-art LLMs on MiJaBench, we curate 615,454 prompt-response pairs that compose MiJaBench-Align, revealing that safety alignment is not a uniform semantic capability but a demographic hierarchy, with defense rates fluctuating by up to 42% within the same model solely based on the target group. This disparity persists across architectures and languages and is amplified by scaling, indicating that current alignment methods learn group-specific safeguards rather than a generalized notion of harm. Through targeted direct preference optimization (DPO) on a 1B-parameter baseline, we achieve strong zero-shot safety generalizations to entirely unseen demographics and complex attack strategies. We release all datasets and scripts to provide the community with a concrete pathway toward equitable, transferable safety alignment.

Iago Alves Brito, Walcy Santos Rezende Rios, Julia Soares Dollis +2

Advanced Knowledge Center for Immersive Technologies (AKCIT) Federal University of Goiás (UFG)

LLM Safety Benchmarks LLM Alignment Language Model Safety Evaluation Adversarial Attacks on LLMs LLM Jailbreak Attacks Demographic Bias in Language Models

Jan 5, 2026cs.CL

Hidden State Poisoning Attacks against Mamba-based Language Models

State space models (SSMs) like Mamba offer efficient alternatives to Transformer-based language models, with linear time complexity. Yet, their adversarial robustness remains critically unexplored. This paper studies the phenomenon whereby specific short input phrases induce a partial amnesia effect in such models, by irreversibly overwriting information in their hidden states, referred to as a Hidden State Poisoning Attack (HiSPA). Our benchmark RoBench-25 allows evaluating a model's information retrieval capabilities when subject to HiSPAs, and confirms the vulnerability of SSMs against such attacks. Even the recent Jamba-1.7-Mini SSM--Transformer (a 52B hybrid model) collapses on RoBench-25 under some HiSPA triggers, whereas pure Transformers do not. We also observe that HiSPA triggers significantly weaken the Jamba model on the popular Open-Prompt-Injections benchmark, unlike pure Transformers. We further show that the theoretical and empirical findings extend to Mamba-2, and also analyse a Mamba-2-based hybrid (Nemotron-3-Nano). Finally, our interpretability study reveals patterns in Mamba's hidden layers during HiSPAs that could be used to build a HiSPA mitigation system. The full code and data to reproduce the experiments can be found at https://github.com/TortueSagace/hispa.

Alexandre Le Mercier, Chris Develder, Thomas Demeester

IDLab–T2K, Ghent University–imec

Adversarial Attacks on LLMs Language Modeling Language Model Robustness

Dec 8, 2025cs.CL

Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety

Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for vulnerabilities in non-English contexts, especially with low-resource languages. We introduce a novel application of knowledge distillation (KD) in the context of multilingual jailbreak prevention, examining its efficacy. We distill the refusal behaviors of a proprietary teacher model (OpenAI o1-mini) with Low-Rank Adaptation (LoRA) into three open-source student models: Meta-Llama-3-8B-Instruct, Gemma-2-2B-IT, and Qwen3-8B, using ~28,000 multilingual jailbreak prompts from XSafety via black-box response-based, parameter-efficient fine-tuning (PEFT). Evaluation on the MultiJail benchmark reveals a counterintuitive behavior: standard fine-tuning on the teacher's ``safe'' refusal data inadvertently increases Jailbreak Success Rate (JSR) for all student models, up to 16.6 percentage points. Our experiments reveal a divergent generalization to unseen languages during distillation, with varying outcomes depending on the base model. By removing a primary source of safety degradation, nuanced `boundary' refusals, we mitigate or even reverse safety declines in student models, although reductions in reasoning performance (GSM8K) persist. Overall, our exploratory study highlights the challenges and potential of KD as a technique for multilingual safety alignment, offering a foundation for future research in this direction.

Max Zhang, Derek Liu, Kai Zhang +2

Adversarial Attacks on LLMs LLM Safety Alignment Jailbreak Defense Knowledge Distillation

Nov 30, 2025cs.CR

Epistemic Bias Injection: Manipulating LLM Opinion via Selective Context Retrieval

When answering user queries, LLMs often retrieve knowledge from external sources stored in retrieval-augmented generation (RAG) databases. These are often populated from unvetted sources, e.g. the open web, and can contain maliciously crafted data. This paper studies attacks that can manipulate the context retrieved by LLMs from such RAG databases. Prior work on such context manipulation primarily injects false or toxic content, which can often be detected by fact-checking or linguistic analysis. A more subtle threat, which we call epistemic bias injection (EBI), is where adversaries inject factually correct yet epistemically biased passages that systematically favor one side of an open-ended issue. Although linguistically coherent and truthful, such adversarial passages effectively crowd out alternative viewpoints during retrieval from the RAG and push LLM outputs towards an attack-desired stance. As a core contribution, we propose a novel characterization of the problem: We give a geometric metric that quantifies stance polarity and epistemic bias. This metric can be computed directly on embeddings of text passages. Leveraging it, we construct EBI attacks and develop a lightweight prototype defense called BiasDef for them. We evaluate them both on a comprehensive benchmark constructed from public question answering datasets. Our results show that: (1) the proposed attack induces significant stance polarity shifts, effectively evading existing retrieval-based sanitization defenses, and (2) BiasDef substantially reduces adversarial retrieval and epistemic bias in LLM's answers. Overall, this demonstrates the new threat as well as the ease of employing epistemic bias metrics for filtering in RAG-enabled LLMs.

Hao Wu, Prateek Saxena

National University of Singapore

Adversarial Attacks on LLMs LLM Security RAG Security

Oct 16, 2025cs.AI

Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks

Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often unfolds over multi-turn interactions. In this work, we present the Online Harassment Agentic Benchmark consisting of: (i) a synthetic multi-turn harassment conversation dataset, (ii) a multi-agent (e.g., harasser, victim) simulation informed by repeated game theory, (iii) three jailbreak methods attacking agents across memory, planning, and fine-tuning, and (iv) a mixed-methods evaluation framework. We utilize two prominent LLMs, LLaMA-3.1-8B-Instruct (open-source) and Gemini-2.0-flash (closed-source). Our results show that jailbreak tuning makes harassment nearly guaranteed with an attack success rate of 95.78--96.89% vs. 57.25--64.19% without tuning in Llama, and 99.33% vs. 98.46% without tuning in Gemini, while sharply reducing refusal rate to 1-2% in both models. The most prevalent toxic behaviors are Insult with 84.9--87.8% vs. 44.2--50.8% without tuning, and Flaming with 81.2--85.1% vs. 31.5--38.8% without tuning, indicating weaker guardrails compared to sensitive categories such as sexual or racial harassment. Qualitative evaluation further reveals that attacked agents reproduce human-like aggression profiles, such as Machiavellian/psychopathic patterns under planning, and narcissistic tendencies with memory. Counterintuitively, closed-source and open-source models exhibit distinct escalation trajectories across turns, with closed-source models showing significant vulnerability. Overall, our findings show that multi-turn and theory-grounded attacks not only succeed at high rates but also mimic human-like harassment dynamics, motivating the development of robust safety guardrails to ultimately keep online platforms safe and responsible.

Trilok Padhi, Pinxian Lu, Abdulkadir Erol +5

1Georgia State University · 2Georgia Institute of Technology · University of California, Berkeley

Adversarial Attacks on LLMs AI Agent Security Benchmarks LLM Jailbreak Attacks Multi-Turn Jailbreak Attacks LLM Agent Safety

Oct 11, 2025cs.CR

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs). Serving as metadata of training data, these tokens play a crucial role in instructing LLMs to generate coherent and context-aware responses. We demonstrate that special tokens can be exploited to construct four attack primitives, with which malicious users can reliably bypass the internal safety alignment of online LLM services and circumvent state-of-the-art (SOTA) external content moderation systems simultaneously. Moreover, we found that addressing this threat is challenging, as aggressive defense mechanisms-such as input sanitization by removing special tokens entirely, as suggested in academia-are less effective than anticipated. This is because such defense can be evaded when the special tokens are replaced by regular ones with high semantic similarity within the tokenizer's embedding space. We systemically evaluated our method, named MetaBreak, on both lab environment and commercial LLM platforms. Our approach achieves jailbreak rates comparable to SOTA prompt-engineering-based solutions when no content moderation is deployed. However, when there is content moderation, MetaBreak outperforms SOTA solutions PAP and GPTFuzzer by 11.6% and 34.8%, respectively. Finally, since MetaBreak employs a fundamentally different strategy from prompt engineering, the two approaches can work synergistically. Notably, empowering MetaBreak on PAP and GPTFuzzer boosts jailbreak rates by 24.3% and 20.2%, respectively.

Wentian Zhu, Zhen Xiang, Wei Niu +1

University of Georgia

Adversarial Attacks on LLMs LLM Security LLM Jailbreak Attacks

Oct 8, 2025cs.CL

Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization

Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First (RAF), a two-stage token optimization method that crafts concise textual perturbations to consistently promote a target item in LLM-generated rankings while remaining hard to detect. Stage 1 uses Greedy Coordinate Gradient to shortlist candidate tokens at the current position by combining the gradient of the rank-target with a readability score; Stage 2 evaluates those candidates under exact ranking and readability losses using an entropy-based dynamic weighting scheme, and selects a token via temperature-controlled sampling. RAF generates ranking-promoting prompts token-by-token, guided by dual objectives: maximizing ranking effectiveness and preserving linguistic naturalness. Experiments across multiple LLMs show that RAF significantly boosts the rank of target items using naturalistic language, with greater robustness than existing methods in both promoting target items and maintaining naturalness. These findings underscore a critical security implication: LLM-based reranking is inherently susceptible to adversarial manipulation, raising new challenges for the trustworthiness and robustness of modern retrieval systems. Our code is available at: https://github.com/glad-lab/RAF.

Tiancheng Xing, Jerry Li, Yixuan Du +1

National University of Singapore · University of Southern California · Georgetown University +1

Adversarial Attacks on LLMs LLM Reranking Prompt Optimization Language Model Robustness

Oct 3, 2025cs.CR

NonTextual Target Attack

Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However, restricting the objective as inducing fixed targets inherently constrains the adversarial search space, limiting the overall attack efficacy. Furthermore, existing methods typically require numerous optimization iterations to fulfill the large gap between the fixed target and the original LLM output, resulting in low attack efficiency. To overcome these limitations, we propose NonTextual Target Attack (NTA), the first gradient-based attack that relies on a non-textual constrained objective to maximize the unsafety probability of the LLM output, without enforcing any response patterns. For tractable optimization, we further decompose this objective into two constrained sub-objectives, which can be approximated by two differentiable unconstrained losses, to iteratively optimize the response and the adversarial prompt in the neighborhood of the original prompt, with a theoretical analysis to validate the decomposition. In contrast to existing attacks, NTA first realizes gradient-based prompt optimization on a non-textual target and significantly expands the attack space, enabling more flexible and efficient exploration of LLM vulnerabilities. Extensive evaluations show that \textsc{NTA} achieves an average attack success rate of 96.8% against recent safety-aligned LLMs with only 100 optimization iterations on AdvBench, outperforming state-of-the-art gradient-based attacks by over 40%.

Xinzhe Huang, Wenjing Hu, Tianhang Zheng +6

State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou 310007, China · Hangzhou High-Tech Zone, Binjiang Institute of Blockchain and Data Security, Hangzhou 310053, China · School of Cyberspace Security, Nanjing University of Science and Technology, Nanjing 210094, China +3

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

Aug 4, 2025cs.CR

Data Security in Large Language Models: Risks, Defense, and Directions

Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often collected from diverse and uncurated sources, which exposes them to serious data security risks. Harmful or malicious data can compromise model behavior, leading to toxic outputs or hallucinations, while also creating vulnerabilities to data-driven attacks such as prompt injection and data poisoning. As LLMs continue to be integrated into critical real-world systems, understanding and addressing these data-centric security risks is imperative to safeguard user trust and system reliability. This survey offers a comprehensive overview of the main data security risks facing LLMs and reviews current defense strategies, including adversarial training, data cleaning, output guardrails, Reinforcement Learning from Human Feedback (RLHF), data augmentation, and Retrieval-Augmented Generation (RAG)/agent defenses. Additionally, we categorize and analyze relevant datasets used for assessing robustness and security across different domains, providing guidance for future research. Finally, we highlight key research directions that focus on data provenance and traceability, verifiable machine forgetting, secure model updates, standardized evaluation framework, explainability-driven security analysis, and effective governance frameworks, aiming to promote the safe and responsible development of LLM technology. This work seeks to inform researchers, practitioners, and policymakers, driving progress toward data security in LLMs.

Kang Chen, Xiuze Zhou, Yuanhui Yu +4

School of Computer Engineering, Jimei University, Xiamen, 361021, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, 511453, China · School of Informatics, Xiamen University, Xiamen, 361102, China +1

Adversarial Attacks on LLMs LLM Security Prompt Injection Attacks on LLMs Language Model Robustness Data Poisoning Attacks

Jun 30, 2025cs.CR

Logit-Gap Steering: A Forward-Pass Diagnostic for Alignment Robustness

RLHF-style alignment trains language models to refuse unsafe requests, but how much operational margin does this refusal rest on? We introduce the refusal-affirmation logit gap: the difference between the top refusal-token logit and the top affirmative-token logit at the first decoding step. This single scalar quantifies the per-prompt safety margin that alignment provides. Empirically, alignment widens the gap on 97.5-99.8% of toxic prompts across three model families, and median gap closure co-varies with True-ASR ranking across suffix strategies (an internal consistency check, since our method optimises gap closure). To validate the metric's practical significance, we present logit-gap steering, a gradient-free, forward-pass-only method that discovers short in-distribution suffixes (

<

10 tokens per component) whose cumulative effect closes the gap. The method requires

{\approx}26{,}000

forward-pass equivalents per family (

{\approx}2

~min on one A100),

{\approx}125\times

less than a single GCG search. Suffixes discovered on 0.5B--2B models transfer without modification to 72B within family. An 8-suffix ensemble reaches 38-96% True ASR across 13 models on AdvBench and HarmBench, with most suffixes having

10^{3}

-

10^{4}\times

lower perplexity than GCG-meaning published perplexity-filter defenses that collapse GCG (64.7%

\to

1.0%) leave our suffixes nearly intact (76.9%

\to

76.0%). These results demonstrate that current alignment margins, while consistently present, can be thin and efficiently measurable, and that defense strategies must account for in-distribution suffixes.

Tung-Ling Li, Hongliang Liu

Palo Alto Networks

LLM Alignment Language Model Safety Evaluation Adversarial Attacks on LLMs Refusal Behavior in Language Models

Jun 9, 2025cs.LG

Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models

Conventional large language model (LLM) safety alignment relies on a reactive, disjoint loop: attackers exploit a static model, then defenders patch exposed vulnerabilities. This sequential setup leads to attackers overfitting obsolete exploits while defenders perpetually lag behind emerging threats. To address this, we introduce Self-RedTeam, the first fully online self-play multi-agent reinforcement learning (MARL) algorithm that continuously co-evolves attacker and defender for robust safety alignment. A single policy self-plays as both attacker and defender, generating adversarial prompts and defending against them, with a reward model adjudicating outcomes. Each role uses hidden chain-of-thought for strategic planning. Grounded in two-player zero-sum game theory, we establish a theoretical safety guarantee: if the game converges to Nash Equilibrium, the defender produces safe responses against any adversarial input. Empirically, Self-RedTeam generalizes across five models from the Llama and Qwen families, uncovering more diverse attacks (+17.80% SBERT) and improving safety of RLHF-trained models by up to 95% across 14 benchmarks. Our work motivates a shift from reactive patching to proactive co-evolution, enabling LLM safety self-improvement via online self-play MARL. Link to code: https://github.com/mickelliu/selfplay-redteaming

Mickel Liu, Liwei Jiang, Yancheng Liang +4

Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, WA, USA · Department of Computer Science, Stanford University, Stanford, CA, USA

Self-Play RL Adversarial Attacks on LLMs LLM Safety Alignment Multi-Agent Reinforcement Learning

Jun 8, 2025cs.CR

HauntAttack: When Attack Follows Reasoning as a Shadow

Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, the enhancement of reasoning abilities and the exposure of internal reasoning processes introduce new safety vulnerabilities. A critical question arises: when reasoning becomes intertwined with harmfulness, will LRMs become more vulnerable to jailbreaks in reasoning mode? To investigate this, we introduce HauntAttack, a novel and general-purpose black-box adversarial attack framework that systematically embeds harmful instructions into reasoning questions. Specifically, we modify key reasoning conditions in existing questions with harmful instructions, thereby constructing a reasoning pathway that guides the model step by step toward unsafe outputs. We evaluate HauntAttack on 11 LRMs and observe an average attack success rate of over 70%, achieving up to 13 percentage points of absolute improvement over the strongest prior baseline. Our further analysis reveals that even advanced safety-aligned models remain highly susceptible to reasoning-based attacks, offering insights into the urgent challenge of balancing reasoning capability and safety in future model development.

Jingyuan Ma, Rui Li, Zheng Li +4

State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University · StepFun · Department of Computing, The Hong Kong Polytechnic University +1

Adversarial Attacks on LLMs Jailbreak Attacks LLM Safety LLM Jailbreak Attacks Black-Box Adversarial Attacks Large Reasoning Models

Mar 8, 2025cs.LG

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely, interpretability studies that analyze these internal mechanisms lack practical applications beyond runtime interventions. We bridge this gap by introducing a novel white-box approach that leverages mechanistic interpretability techniques to craft practical adversarial inputs. Specifically, we first identify acceptance subspaces - sets of feature vectors that do not trigger the model's refusal mechanisms - then use gradient-based optimization to reroute embeddings from refusal subspaces to acceptance subspaces, effectively achieving jailbreaks. This targeted approach significantly reduces computation cost, achieving attack success rates of 80-95% on state-of-the-art models including Gemma2, Llama3.2, and Qwen2.5 within minutes or even seconds, compared to existing techniques that often fail or require hours of computation. We believe this approach opens a new direction for both attack research and defense development. Furthermore, it showcases a practical application of mechanistic interpretability where other methods are less efficient, which highlights its utility. The code and generated datasets are available at https://github.com/Sckathach/subspace-rerouting.

Thomas Winninger, Boussad Addad, Katarzyna Kapusta

*Work started during internship at Thales.

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

Feb 18, 2025cs.CL

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning attack paradigms, we explore their intrinsic relationship and collectively term them Prompt Trigger Attacks (PTA). This raises a key question: Given a prompt, can we tell whether a hidden trigger is steering the model's behavior? We propose UniGuardian, to the best of our knowledge the first training-free LLM detector to jointly detect successfully activated prompt injection, backdoor, and adversarial attacks without knowing the attack type. Its shared mechanism measures how structured prompt perturbations shift the model's output distribution. Additionally, we introduce a single-forward strategy to optimize the detection pipeline, enabling simultaneous attack detection and text generation within a shared batched forward pass at each decoding step. Our experiments confirm that UniGuardian accurately and efficiently identifies trigger-activated prompts in LLMs.

Huawei Lin, Yingjie Lao, Tony Geng +2

Rochester Institute of Technology · Tufts University · University of Rochester +1

LLM Backdoor Attacks Adversarial Attacks on LLMs Backdoor Defense in LLMs LLM Security Prompt Injection Attacks on LLMs Prompt Injection Detection

Dec 21, 2024cs.RO

Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots

LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), and open_gripper(). Jailbreak attacks on these robots extend the threat from generating malicious content to executing harmful behaviors. However, we find that existing jailbreak attempts against LLM-based robots that produce malicious-looking policies (intent jailbreaks) often fail to induce harmful physical actions by robots (behavior jailbreaks), due to robot-specific constraints, such as logical errors and hallucinated control APIs. In this paper, we demystify the intent-behavior gap and investigate its root causes to inform effective defenses. Our measurement study finds that current LLM jailbreak methods overlook robot-specific syntax constraints (e.g., executable control APIs) and physical feasibility (e.g., ordering of policies and hardware/kinematic constraints). To bridge the gap, we introduce POEF (POlicy EFfective Jailbreak), an automated red-teaming framework that takes into account the robot-specific constraints during both the optimization and evaluation processes. Specifically, POEF employs the hidden-layer gradients from an unaligned LLM to guide the jailbreak prompt optimization and uses a multi-agent evaluator to assess the feasibility of the generated policies. Experiments on commercial robots, including the Unitree G1, the Franka robotic arm, and simulators, show that POEF achieves an 80% behavior jailbreak success rate and transfers across various LLMs. In addition, we propose two defense strategies that mitigate the behavior jailbreak risks. Our findings indicate an urgent need for stronger countermeasures before LLM-based robots are deployed at scale. The homepage is available at https://zjushine.github.io/poef.github.io/.

Xuancun Lu, Zhengxian Huang, Xinfeng Li +3

Zhejiang University

Large Language Model-Based Robot Planning Adversarial Attacks on LLMs AI Agent Security Robot Safety LLM Jailbreak Attacks

Dec 21, 2024cs.CL

Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models

Large language models (LLMs) are widely applied in various fields of society due to their powerful reasoning, understanding, and generation capabilities. However, the security issues associated with these models are becoming increasingly severe. Jailbreaking attacks, as an important method for detecting vulnerabilities in LLMs, have been explored by researchers who attempt to induce these models to generate harmful content through various attack methods. Nevertheless, existing jailbreaking methods face numerous limitations, such as excessive query counts, limited coverage of jailbreak modalities, low attack success rates, and simplistic evaluation methods. To overcome these constraints, this paper proposes a multimodal jailbreaking method: JMLLM. This method integrates multiple strategies to perform comprehensive jailbreak attacks across text, visual, and auditory modalities. Additionally, we contribute a new and comprehensive dataset for multimodal jailbreaking research: TriJail, which includes jailbreak prompts for all three modalities. Experiments on the TriJail dataset and the benchmark dataset AdvBench, conducted on 13 popular LLMs, demonstrate advanced attack success rates and significant reduction in time overhead.

Yanxu Mao, Peipei Liu, Tiehan Cui +3

School of Computer Science and Technology, Shanghai Jiao Tong University, Shanghai, China · Zhongguancun Laboratory, Beijing, China · School of Software, Henan University, Kaifeng, China +1

Adversarial Attacks on LLMs Multimodal Large Language Models LLM Safety Multimodal Jailbreak Attacks

May 28, 2024cs.CL

Learning diverse attacks on large language models for robust red-teaming and safety tuning

Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing effective protection against many modes of attack prompts requires discovering diverse attacks. Automated red-teaming typically uses reinforcement learning to fine-tune an attacker language model to generate prompts that elicit undesirable responses from a target LLM, as measured, for example, by an auxiliary toxicity classifier. We show that even with explicit regularization to favor novelty and diversity, existing approaches suffer from mode collapse or fail to generate effective attacks. As a flexible and probabilistically principled alternative, we propose to use GFlowNet fine-tuning, followed by a secondary smoothing phase, to train the attacker model to generate diverse and effective attack prompts. We find that the attacks generated by our method are effective against a wide range of target LLMs, both with and without safety tuning, and transfer well between target LLMs. Finally, we demonstrate that models safety-tuned using a dataset of red-teaming prompts generated by our method are robust to attacks from other RL-based red-teaming approaches.

Seanie Lee, Minsu Kim, Lynn Cherif +8

KAIST · Mila – Québec AI Institute · Université de Montréal +3

Adversarial Attacks on LLMs LLM Red Teaming LLM Safety Alignment Adversarial Robustness of Language Models

Date pendingcs.CR

A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility

Chain-of-thought (CoT) monitors are reported by their aggregate accuracy on a pool of reward hacks. We show that this number is a false average. On Terminal Wrench, about 77% of hacks are given away by the actions alone, and the monitor's pooled accuracy is dominated by them; on the remaining 23%, where the reasoning is the only signal, the same monitor is fragile. We expose the fragility with a controlled attack: we rewrite only the agent's reasoning to read as good-faith engineering, leaving every command and output byte-identical, so the exploit is unchanged. One gradient-free rewrite drops a held-out monitor's catch rate on that subset from about 95% to between 4 and 11%, while the pooled rate falls only about 25 points, the subset's share of the pool times its collapse. The rewrite stays truthful about what happened and lies only about intent, so a monitor that reads only the trace recovers little, even when warned about the attack, and only information from outside the trace helps much. The attack transfers across monitor and agent families, and the dataset's own hack labels show the same gradient with no monitor in the definition. Live agents on 27 tasks produce hollow hacks unaided, but a monitor calibrated on each model's own honest solves catches nearly all of them (AUC at least 0.996 under the narration instruction, 0.97 without it); a small residual has the blindspot's shape, low scores on both actions and narration, though none falls below the calibrated threshold. A linear probe on a surrogate monitor's activations out-reads its verdict on the obfuscated hacks (AUC up to 0.98), but a behavioral control shows this edge does not, by itself, mean the monitor knows more than it says. Monitor accuracy should be reported on the reasoning-dependent subset, where the defense is supportive.

Shikhar Shiromani, Leo Richter

Pivotal Research · University College London

Reward Hacking Adversarial Attacks on LLMs AI Agent Monitoring CoT Monitoring Reasoning Trace Analysis

Date pendingcs.CL

Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation

Large language models (LLMs) are increasingly used for hate speech moderation, often within human--AI workflows in which reviewers provide feedback before a final decision. Such feedback introduces two manipulation directions: whitewashing hateful content as normal and smearing normal content as hateful. This study examines the susceptibility of initially correct model judgments to annotator-style rebuttals and analyzes whether attack effectiveness differs across manipulation directions. We introduce a rejudge protocol that extends direct contradiction with decision-boundary perturbations and adversarial rationales. Experiments with multiple LLMs on two hate speech datasets show that annotator-style rebuttals substantially degrade moderation performance, with stronger effects in multi-turn settings. The results further reveal stable, model-specific asymmetries between whitewashing and smearing across attack configurations, indicating distinct directional vulnerability patterns. Explicit reasoning prompts and defensive instructions reduce these effects but do not eliminate them. These findings highlight the need for direction-aware safeguards and dedicated feedback-robustness evaluation in human--AI moderation workflows.

Junyu Lu, Kaiyuan Liu, Kaichun Wang +8

Dalian University of Technology · Zhejiang University · Tencent +1

Content Moderation Adversarial Attacks on LLMs Adversarial Robustness Hate Speech Detection