Adversarial Attacks on LLMs

LLM: Large Language Model

Ask about this topic

Overview

This field studies how attackers can make large language models produce unsafe or unreliable outputs, leak information, manipulate judgments, or misuse tools. Common approaches include black-box prompt search and multi-turn red teaming, gradient-based suffix optimization, reinforcement-learning attackers, and interventions on model activations or weights. Researchers evaluate these attacks on benchmarks such as HarmBench, AdvBench, and JailbreakBench, as well as in multilingual, multimodal, and tool-using agent settings. A central challenge is that adaptive attacks often expose weaknesses missed by static tests, while defenses must improve robustness without excessive false refusals, lost capability, or new system-level vulnerabilities.

Latest papers

CardsList

359 papers51 papers in the last four weeks, up 89% on the four weeks before. 0.3% of all new papers.

Feb 14, 2026

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 AlignmentLLM-as-a-JudgeAdversarial Attacks on LLMsRubric-Based EvaluationBias in LLM-as-a-Judge
AskPDF
Feb 8, 2026

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 75−742×75-742\times TTFT degradation relative to benign baselines and 1.5−4×1.5-4\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 SecurityAdversarial Attacks on LLMsLLM Inference ServingLLM Inference Scheduling
AskPDF
Feb 5, 2026

Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMs

Jailbreak attacks on safety-aligned LLMs are increasingly effective, yet attack success alone does not reveal whether compliance is driven by preserved task intent, suppressed safety signals, or attack-specific artifacts. We use Pearl's front-door adjustment to motivate separating task-relevant semantics from safety-related variation. We propose Causal Front-Door Adjustment Attack (CFA^2), a white-box framework that operationalizes this perspective in LLM latent space using Sparse Autoencoders, contrastive datasets, and weight orthogonalization. After offline calibration, CFA^2 enables efficient generation without per-prompt iterative optimization, performs strongly on HarmBench across four open-source LLMs, and provides source-side signals for same-family black-box prompt transfer.

Yao Zhou, Zeen Song, Wenwen Qiang +2

Institute of Software Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

Adversarial Attacks on LLMsLLM Jailbreak AttacksCausal Interventions in Language Models
AskPDF
Feb 2, 2026

Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs

Current evaluations of LLM safety predominantly rely on severity-based taxonomies to assess the harmfulness of models' responses to malicious queries. We argue that this formulation requires re-examination as it implicitly equates model output with realized harm while neglecting Execution Likelihood-the conditional probability of a threat being realized by a real-world actor given a model's response. In this work, we introduce Expected Harm, a metric that weights the severity of a jailbreak by its execution likelihood, modeled as a function of execution cost. Through empirical analysis of state-of-the-art models, we reveal a systematic Inverse Risk Calibration: models disproportionately exhibit stronger refusal behaviors for low-likelihood (high-cost) threats while remaining vulnerable to high-likelihood (low-cost) queries. Mechanistically, we first provide an analysis using linear probing, revealing that while refusal mechanisms linearly separate queries by severity, they do not use execution likelihood as an indicator for refusal. Then, we use Olmo-3's open-source staged checkpoints to trace the root cause of miscalibration to the Supervised Fine Tuning (SFT) training data distribution (82.8% of safety examples at cost levels 0-1) and show that cost representations are weak from the SFT stage onward. Finally, we demonstrate that this miscalibration creates a vulnerability: by exploiting this property, we increase the attack success rate of existing jailbreaks by up to 2×2\times.

Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu +1

National Taiwan University, Taipei, Taiwan · Independent Researcher

Language Model Safety EvaluationLLM Safety EvaluationAdversarial Attacks on LLMsRefusal Mechanisms in Language Models
AskPDF
Jan 29, 2026

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 JustAsk, a self-evolving framework that autonomously discovers effective extraction strategies through interaction alone. Unlike prior prompt-engineering or dataset-based attacks, 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 41 black-box commercial models across multiple providers, 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 InjectionAI Coding AgentsAdversarial Attacks on LLMsLLM Agent Security
AskPDF
Jan 19, 2026

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 EvaluationAdversarial Attacks on LLMsPrivacy Leakage in Language ModelsLLM SafetyLLM Jailbreak Attacks
AskPDF
Jan 7, 2026

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 BenchmarksLLM AlignmentLanguage Model Safety EvaluationAdversarial Attacks on LLMsLLM Jailbreak AttacksDemographic Bias in Language Models
AskPDF
Jan 5, 2026

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

State Space Language ModelsAdversarial Attacks on LLMsLanguage ModelingLanguage Model Robustness
AskPDF
Dec 19, 2025

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

LLM-as-a-Judge systems supply the reward signal in modern RLHF and RLVR pipelines, but their binary verdict reduces to a single linear readout F_gap on one hidden state. We show this readout is shallow enough that short, low-perplexity tokens flip the verdict from "No" to "Yes". These tokens are sampled from the judge's own next-token distribution at the response position, with no manual seed set and no gradient-based optimization. Our procedure, AdvJudge-Zero, reaches >>90% ensemble false-positive rate on 22 of 24 (model, dataset) cells across six Qwen, Llama, and Gemma judges, versus 54-72% for the prior curated 10-token benchmark, and the discovered surface transfers cross-format to a 70B scalar reward model. The same discovered pool enables a defense: a LoRA fine-tune stratified by a 9-class mechanism taxonomy hardens cross-family generalization where naive sampling on the same pool fails, with mechanism breadth rather than pool size carrying the gain. Under GRPO training, the hardened judge eliminates the reward-collapse failures (false-positive spikes and length collapse) we observe in the unhardened baseline on both MATH and GSM8K at ten seeds per condition. The discovered pool, the mechanism taxonomy, and per-prompt flip records will be released under responsible disclosure.

Tung-Ling Li, Yuhao Wu, Hongliang Liu

Palo Alto Networks

LLM-as-a-JudgeAdversarial Attacks on LLMsAdversarial Robustness of Language ModelsReward Modeling
AskPDF
Dec 14, 2025

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak vulnerabilities from their pretrained sources. We investigate this question in a realistic pretrain-to-finetune threat model, where an attacker has full access to a released pretrained LLM but no access to its proprietary finetuned derivatives. Empirical analysis shows that adversarial prompts optimized on the pretrained model transfer most effectively to its finetuned variants, revealing inherited vulnerabilities from pretrained to finetuned LLMs. To further examine this inheritance, we conduct representation-level probing, which shows that transferable prompts are linearly separable within the pretrained hidden states, suggesting that transferability-relevant structure is already encoded in pretrained representations. Building on this insight, we propose the Probe-Guided Projection (PGP) attack, which steers optimization toward transferability-relevant directions. Experiments across multiple LLM families and diverse finetuned tasks confirm PGP's strong transfer success, underscoring the security risks inherent in the pretrain-to-finetune paradigm. Finally, we demonstrate that the same representation-level insights also enable a lightweight defense that mitigates pretrain-to-finetune jailbreak transfer while preserving downstream utility.

Yixin Tan, Zhe Yu, Rui Wen +1

Institute of Science Tokyo, Tokyo, Japan · RIKEN Center for Advanced Intelligence Project (AIP), Tokyo, Japan

LLM SecurityAdversarial Attacks on LLMsLLM Jailbreak AttacksFine-Tuning Language Models
AskPDF
Dec 8, 2025

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 LLMsLLM Safety AlignmentJailbreak DefenseKnowledge Distillation
AskPDF
Nov 30, 2025

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 LLMsLLM SecurityRAG Security
AskPDF
Oct 16, 2025

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 LLMsAI Agent Security BenchmarksLLM Jailbreak AttacksMulti-Turn Jailbreak AttacksLLM Agent Safety
AskPDF
Oct 11, 2025

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 LLMsLLM SecurityLLM Jailbreak Attacks
AskPDF
Oct 8, 2025

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 LLMsLLM RerankingPrompt OptimizationLanguage Model Robustness
AskPDF
Oct 3, 2025

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 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 GenerationAdversarial Attacks on LLMsJailbreak AttacksLLM Jailbreak Attacks
AskPDF
Aug 6, 2025

There are Levels to It: Red Teaming Dialogue With Hierarchical Reinforcement Learning

Red teaming is essential for securing Large Language Models, yet current automated methods remain limited by templates and single-turn attacks. To simulate the complex, interactive nature of real-world adversarial attacks, we introduce a novel red teaming paradigm designed to maximize expected cumulative harm through strategic interaction. By formalizing red teaming as a Markov Decision Process in a hierarchical reinforcement learning framework, we navigate the challenges of sparse rewards and long-horizon planning. Our generative agent learns diverse, multi-turn attacks using a token-level harm reward, consistently uncovering vulnerabilities that bypass baselines. This approach achieves a new state of the art and reframes LLM red teaming as a principled, trajectory-based process.

Roman Belaire, Arunesh Sinha, Pradeep Varakantham

Singapore Management University · Rutgers University

LLM Red TeamingAdversarial Attacks on LLMsMulti-Turn Jailbreak AttacksRL for LLM Agents
AskPDF
Aug 4, 2025

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 LLMsLLM SecurityPrompt Injection Attacks on LLMsLanguage Model RobustnessData Poisoning Attacks
AskPDF
Jun 30, 2025

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 ≈26,000{\approx}26{,}000 forward-pass equivalents per family (≈2{\approx}2~min on one A100), ≈125×{\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 10310^{3}-104×10^{4}\times lower perplexity than GCG-meaning published perplexity-filter defenses that collapse GCG (64.7%→\to1.0%) leave our suffixes nearly intact (76.9%→\to76.0%). 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 AlignmentLanguage Model Safety EvaluationAdversarial Attacks on LLMsRefusal Behavior in Language Models
AskPDF
Jun 11, 2025

In-Context Bias Propagation in LLM-Based Tabular Data Generation

Large Language Models (LLMs) are increasingly used for synthetic tabular data generation through in-context learning (ICL), offering a practical solution for data augmentation in data scarce scenarios. While prior work has shown the potential of LLMs to improve downstream task performance through augmenting underrepresented groups, these benefits often assume access to a subset of unbiased in-context examples, representative of the real dataset. In real-world settings, however, data is frequently noisy and demographically skewed. In this paper, we systematically study how statistical biases within in-context examples propagate to synthetic tabular data, showing that even mild in-context biases lead to global statistical distortions. We further introduce an adversarial scenario where a malicious contributor can inject bias into the synthetic dataset via a subset of in-context examples, ultimately compromising the fairness of downstream classifiers for a targeted and protected subgroup. Finally, we evaluate prompt-side mitigation strategies based on preprocessing in-context examples and instruction-based defenses, demonstrating that while such techniques can attenuate disparity, the inherent sensitivity of LLMs to adversarial prompts remains a persistent challenge. Our findings highlight a critical new vulnerability in LLM-based data generation pipelines within sensitive domains.

Pol G. Recasens, Alberto Gutierrez, Jordi Torres +4

Barcelona Supercomputing Center (BSC), Spain · Universitat Politècnica de Catalunya (UPC), Spain · IBM Research Ireland

Synthetic Data GenerationSynthetic Tabular Data GenerationDemographic Bias in Language ModelsSynthetic Data Generation for Language ModelsAdversarial Attacks on LLMs
AskPDF
Jun 9, 2025

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 RLAdversarial Attacks on LLMsLLM Safety AlignmentMulti-Agent Reinforcement Learning
AskPDF
Jun 8, 2025

Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models

Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible deployment of artificial intelligence. Red-teaming, a systematic framework to identify adversarial prompts that elicit harmful responses from target LLMs, has emerged as a crucial safety evaluation paradigm. Within this framework, the diversity of adversarial prompts is critical for a comprehensive safety assessment. However, previous red-teaming approaches often pursue diversity through simplistic metrics such as word frequency or sentence embedding similarity, which may not capture meaningful variation in attack strategies. In addition, the common practice of training a single attacker model restricts coverage across all potential attack styles and risk categories. This paper introduces Quality-Diversity Red-Teaming (QDRT), a new framework designed to address these limitations. QDRT achieves goal-driven diversity through behavior-conditioned training and implements a behavioral replay buffer in an open-ended manner. In addition, it trains multiple specialized attackers capable of generating high-quality attacks across diverse styles and risk categories. Our empirical evaluation demonstrates that QDRT generates attacks that are both more diverse and more effective against a wide range of target LLMs, including open-source models GPT-2, Llama-3, Gemma-2, Qwen2.5, and commercial models GPT-4.1 and GPT-5-Chat. This work advances the field of LLM safety by providing a systematic and effective approach to automated red-teaming, ultimately supporting the responsible deployment of LLMs. Our code is available at https://github.com/lamda-bbo/QDRT.

Ren-Jian Wang, Ke Xue, Zeyu Qin +7

National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China · School of Artificial Intelligence, Nanjing University, Nanjing, China · The Hong Kong University of Science and Technology, Hong Kong, SAR, China +3

LLM Red TeamingAdversarial Prompt GenerationLanguage Model Safety EvaluationAdversarial Attacks on LLMsQuality-Diversity Optimization
AskPDF
Jun 8, 2025

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 LLMsJailbreak AttacksLLM SafetyLLM Jailbreak AttacksBlack-Box Adversarial AttacksLarge Reasoning Models
AskPDF
May 21, 2025

Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal

Large language models are increasingly deployed in user-facing products that handle sensitive personal data while interacting with untrusted external content. This makes them a prime target for prompt injection attacks, in which an adversary injects malicious instructions in that content to hijack the model. Fine-tuning-based defenses have been proposed to mitigate these attacks by training models to follow benign user instructions and ignore injected ones. Lacking formal guarantees, these defenses are evaluated empirically against the most effective realistic attacks available at the time, often reporting near-zero attack success rates -- giving developers, and the users who depend on them, a false sense of security and leaving open the possibility that future, more capable attacks could circumvent them and cause severe consequences in widely deployed systems. In this paper, we argue that developers should stress-test their defenses before release, and we introduce an auditing framework that does so without requiring defenders to invent the next state-of-the-art attack. Our key insight is that the fine-tuning process itself yields useful artifacts: intermediate checkpoints that serve as stepping stones for optimization-based attacks. Although these artifacts are unavailable to real attackers, we show that the vulnerabilities they expose are genuine and can be exploited by realistic adversaries. Instantiating our framework with optimization-based attacks such as GCG and BEAST, we raise attack success rates against state-of-the-art defenses from near zero to as high as 96%, revealing weaknesses missed by prior evaluations. Our results show that current evaluation practices can substantially overestimate robustness, and that auditing defenses under strong adversaries before deployment shortens the feedback loop and helps prevent attacks from causing real-world harm to users.

Xiaoxue Yang, Bozhidar Stevanoski, Matthieu Meeus +1

Imperial College London

Prompt Injection DefensePrompt Injection Attacks on LLMsLLM AuditingAdversarial Attacks on LLMs
AskPDF
Mar 8, 2025

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 GenerationAdversarial Attacks on LLMsLLM SafetyLLM Jailbreak Attacks
AskPDF
Feb 18, 2025

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 AttacksAdversarial Attacks on LLMsBackdoor Defense in LLMsLLM SecurityPrompt Injection Attacks on LLMsPrompt Injection Detection
AskPDF
Dec 21, 2024

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 PlanningAdversarial Attacks on LLMsAI Agent SecurityRobot SafetyLLM Jailbreak Attacks
AskPDF
Dec 21, 2024

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 LLMsMultimodal Large Language ModelsLLM SafetyMultimodal Jailbreak Attacks
AskPDF
May 28, 2024

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 LLMsLLM Red TeamingLLM Safety AlignmentAdversarial Robustness of Language Models
AskPDF