Jailbreak Attacks

Ask about this topic

Momentum

13 papers in the last four weeks, up 30% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 154

All topics
CardsList

  1. CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion

    Sep 30, 2026Zhen Liang, Hai Huang, Wentao ChenJailbreak AttacksVulnerable Code

    School of Computer Science and Technology, Zhejiang Sci-Tech University · Zhejiang Key Laboratory of Digital Fashion and Data Governance, Zhejiang Sci-Tech University · China Academy of Information and Communications Technology

  2. SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

    Sep 30, 2026Wenyu Chen, Li Wang, Chuanchao Zang +5Jailbreak AttacksVideo Multimodal Large Language Models

    Shandong University

  3. ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs

    Sep 29, 2026Xianhui Zhang, Jian Yu, Chengyu Xie +6Multilingual SafetyLarge Language Model Safety

    Nanjing University of Science and Technology, Nanjing, China · National University of Singapore, Singapore · Beihang University, Beijing, China

  4. CollageAttack: Exploiting Cross-Modal Alignment Flaws in T2I Models through Spatial Text Composition

    Sep 29, 2026Zhiyi Mou, Yao Lu, Wangze Ni +6Text-To-ImageWhite-Box Spectral-Subspace-Guided Attack

    Zhejiang University · Hong Kong Polytechnic University

  5. Controlled Decoding Attacks on Black-Box LLMs

    Sep 29, 2026Jesson Wang, Shawn Li, Wei Yang +4Large Language Model JailbreaksJailbreak Attacks

    University of Southern California · Adobe · Amazon

  6. SafeMol: Dual-Modality Safety Alignment for Molecular Multimodal Models

    Sep 27, 2026Xinmiao Wang, Ruijie Wang, Menghui Wang +5Safety AlignmentSafer

    Beihang University · China CITIC Bank · Stable AI +1

  7. On the Efficiency-Safety Dilemma in Large Reasoning Models

    Sep 20, 2026Yifei Yang, Zouying Cao, Xingrui Wang +4Large Reasoning ModelsJailbreak Attacks

    AGI Institute, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University · Ant Group +2

  8. Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models

    Sep 16, 2026Youjia Wang, Lin Xu, Yang Sun +3Large Language Model SafetyJailbreak Attacks

    Huawei Technology Inc

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

    Sep 14, 2026Md Jueal Mia, Yanzhao Wu, Selcuk Uluagac +1Jailbreak AttacksJailbreaks

    Knight Foundation School of Computing and Information Sciences, Florida International University, USA · Security, Optimization, and Learning for InterDependent Networks (solid) Laboratory, Miami, Florida, USA

  10. Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models

    Sep 10, 2026Syed Ghazanfar Abbas, Dongyan XuAuthenticationJailbreak Attacks

    Purdue University

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

    Sep 10, 2026Thomas RivasseauLarge Language Model JailbreaksLarge Language Model Safety

    School of Information Studies McGill University

  12. Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning

    Sep 8, 2026Tejasvi C. AddagadaLarge Language Model JailbreaksJailbreak Attacks

    Independent researcher

  13. The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation

    Sep 7, 2026Peng Li, Qianqian Xu, Yangbangyan Jiang +2Generative Video ModelsVideo Generation

    School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China +1

  14. IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks

    Sep 3, 2026Saikat Mondal, Mamta, Deeksha Varshney +2Large Language Model SafetyLarge Language Model Evaluation

    Indian Institute of Technology Jodhpur, Jodhpur, India · King’s College London, London, UK · Indian Institute of Technology Patna, Patna, India

  15. Validity-Aware Jailbreak Evaluation for Large Language Models

    Aug 31, 2026Qilong Wu, Sahil Wadhwa, Pranab Mohanty +2Large Language Model JailbreaksJailbreak Attacks

    University of Illinois Urbana-Champaign · Capital One

  16. The Fragility of Jailbreak Robustness Across Operational States

    Aug 31, 2026Yuna Park, Hwang Youn Kim, Yujin Kim +3Jailbreak AttacksAttack-Success Rate

    Yonsei University · Korea Institute of Science and Technology (KIST) · Korea University +1

  17. The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

    Aug 31, 2026Md Mokarram Chowdhury, Ernie Chang, Yang LiJailbreaksJailbreak Attacks

    Department of Computer Science, Iowa State University, United States · Meta, United States

  18. TACS: Trajectory-Aware Candidate Selection for LLM Jailbreak Suffix Optimization

    Aug 30, 2026Shiliang XiaoJailbreak AttacksJailbreaks

  19. Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models

    Aug 27, 2026Benlei Cui, Shen Pang, Yuke Wang +7Jailbreak Attacks

    1Yuvion Team, Alibaba Group · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, School of Statistics and Data Science, Zhejiang Gongshang University

  20. TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

    Aug 16, 2026Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu +1Jailbreak AttacksTrajectory-Aware Hidden-State Analyses

    Texas A&M University · Amazon

  21. Stealing Reasoning Traces from Proprietary LLM APIs

    Aug 10, 2026Alexander Panfilov, David Schmotz, Ilia Shumailov +5LLM Reasoning StrategiesReasoning Traces

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

  22. Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks

    Aug 10, 2026Mingyu Luo, Ming Deng, Zilang Qiu +8Jailbreak AttacksAttack-Success Rate

    College of Computer Science and Artificial Intelligence, Fudan University · School of Computer Engineering and Science, Shanghai University · Beijing Normal University +5

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

    Aug 10, 2026Hongli Shen, Shaopeng Fu, Qinbo Zhang +2Safety AlignmentJailbreak Attacks

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

  24. Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production

    Aug 9, 2026Cong Ming, Jingyi Chen, Bin Liu +4GuardrailLarge Language Model Safety

    University of Science and Technology of China · Shenzhen University · Sangfor Technologies

  25. ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization

    Aug 4, 2026Hujian Zhu, Yihao Huang, Felix Juefei-Xu +5Jailbreak AttacksWhite-Box Spectral-Subspace-Guided Attack

    East China Normal University, Shanghai, China · New York University, New York, USA · The Hong Kong Polytechnic University, Hong Kong, China +2

  26. Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks

    Aug 2, 2026Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2Jailbreak AttacksLLM Defense Mechanisms

  27. Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

    Aug 2, 2026Wanguang Li, Zhaoxin Wang, Handing WangAdversarial PromptsJailbreak Success Rates

    School of Artificial Intelligence, Xidian University, Shaanxi, China

  28. Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks

    Jul 30, 2026Youting Wang, Xiao Han, Dingyan Shang +2Safety BenchmarksSecurity Evaluation

  29. Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses

    Jul 29, 2026Haoyu Zhang, Shibo Zheng, Xiangchen Guan +4LLM Defense MechanismsAttack-Success Rate

    1Northeastern University

  30. Prosody-driven Jailbreaks in Audio LLMs: A Controlled Study and Mechanistic Analysis

    Jul 29, 2026Jiachen Qian, Junyu LiText-To-AudioLarge Audio Language Models

    City University of Hong Kong · City University of Hong Kong (Dongguan)

  31. Geometric Configurations of Perturbed Jailbreak Prompts

    Jul 22, 2026Lynn Delcon, Andres Algaba, Vincent GinisLarge Language Model JailbreaksJailbreak Attacks

    Department of Business Technology and Operations, Data Analytics Laboratory, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium · imec-SMIT, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Brussels, Belgium · School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA

  32. Visual Token Compression Enhances Robustness of MLLMs

    Jul 21, 2026Shishen Gu, Jiequan Cui, Wenbo Hu +3Visual Token PruningRecent Vision-Language Models

    Hefei University of Technology · Hefei, China

  33. An Early Warning of Emerging Biosecurity Risks in Frontier LLMs

    Jul 20, 2026Zhida He, Xia Hu, Baichen Le +20Large Language Model SafetyLife Sciences Research

    Shanghai Artificial Intelligence Laboratory

  34. JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models

    Jul 20, 2026Qingjia Huang, Jingyu Zhang, Jianguo Wu +6Large Language Model JailbreaksJailbreak Attacks

    Institute of Information Engineering, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Renmin University of China +2

  35. Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models

    Jul 19, 2026Xingkai Peng, Jun Jiang, Jiayang Liu +2Text-To-Video Generation ModelJailbreak Attacks

    University of Science and Technology of China

  36. How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions

    Jul 19, 2026Yukai Zhou, Feiyang Lu, Xiaokai Mao +2Jailbreak AttacksJailbreaks

    ShanghaiTech University · Zhejiang University

  37. Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents

    Jul 4, 2026Abhishek Kumar, Carsten MapleCoding AgentsLarge Language Model Safety

    The Alan Turing Institute, London, United Kingdom

  38. Overloading Large Vision-Language Models for Jailbreaking

    Jul 3, 2026Haoyu Zhang, Yangyang Guo, Mohan KankanhalliLarge Language Model JailbreaksJailbreak Attacks

    1National University of Singapore · 2Hangzhou International Innovation Institute, Beihang University

  39. Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

    Jul 1, 2026Junlong Liu, Haobo Wang, Weiqi Luo +1Jailbreak AttacksPrompt Engineering

    1Sun Yat-sen University · 2Nanyang Technological University

  40. Robust Harmful Features Under Jailbreak Attacks: Mechanistic Evidence from Attention Head Specialization in Large Language Models

    Jun 26, 2026Yanchen Yin, Dongqi Han, Linghui LiJailbreak AttacksLarge Language Model Safety

    Beijing University of Posts and Telecommunications, Beijing, China.

  41. Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries

    Jun 25, 2026Prarabdh Shukla, Ritik, Suhas Rao +2Jailbreak AttacksMalicious Agents

    Centre for Machine Intelligence and Data Science, IIT Bombay · Department of Computer Science and Engineering, IIT Bombay

  42. VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

    Jun 24, 2026Yining Sun, Haoyu Kang, Jiajun Wu +7Video GenerationJailbreak Attacks

    1Tsinghua University · 3Central South University · 4South China Normal University +3

  43. PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation

    Jun 23, 2026Leyi Sheng, Han Sun, Zhen Sun +4Text-To-ImageJailbreak Attacks

    1The Hong Kong University of Technology and Science (Guangzhou) · 2East China Normal University · 3Shanghai Qi Zhi Institute +4

  44. IndicGuard: A Multilingual Safety Guard Model and Dataset for Indic Languages

    Jun 22, 2026Parth Bramhecha, Smit Deshmukh, Sairaj Bodhale +2Multilingual SafetyLarge Language Model Safety

    L3Cube-Labs, Pune

  45. OTTER: A Red-Teaming System for Toxicity-Evading Jailbreak Prompt Optimization

    Jun 19, 2026Jerry Wang, Hsin-Ling Hsu, Yi-Cheng Lai +2ToxicityRed-Teaming

    1National Chengchi University, Taipei, Taiwan

  46. A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models

    Jun 16, 2026Nicola FrancoJailbreak AttacksRed-Teaming

    Head of AI Security Lab The Italian Institute of Artificial Intelligence (AI4I) Corso Castelfidardo 22, 10129 Turin, Italy

  47. Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models

    Jun 15, 2026Ke Miao, Jiaxin Li, Hongliang Chen +2Large Language Model SafetyLarge Reasoning Models

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou HighTech Zone (Binjiang) Blockchain and Data Security Research Institute, China · Li Auto Inc. +2

  48. Automated jailbreak attack targeting multiple defense strategies

    Jun 15, 2026Qi Wang, Chengcheng Wan, Weijia He +4Attacker Large Language ModelJailbreak Attacks

    East China Normal University Shanghai, China · East China Normal University, Shanghai Innovation Institute Shanghai, China · University of Southampton Southampton, England +2

  49. DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing

    Jun 15, 2026Xuanyu Yin, Yilin Jiang, Jun Zhou +3Jailbreak AttacksJailbreaks

    East China Normal University Shanghai, China · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China · Institute of Information Engineering, Chinese Academy of Sciences Beijing, China

  50. BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems

    Jun 12, 2026Leonhard Waibl, Felix Michalak, Hadrien MariacciaJailbreak AttacksFirst Comprehensive Benchmark

    University of Graz, Graz, Austria · Supervised Program for Alignment Research (SPAR) · Centre pour la Sécurité de l’IA (CeSIA), Paris, France.

  51. FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization

    Jun 11, 2026Jianwei Wang, Guoyang Shen, Yanhong Wu +5Streaming GuardrailsLarge Language Model Safety

    South China University of Technology · BUAA

  52. Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

    Jun 10, 2026Yitong Zhang, Shiteng Lu, Jia LiLarge Language Model JailbreaksJailbreak Attacks

    College of AI Tsinghua University Beijing, China · Yingcai Honors College University of Electronic Science and Technology of China Chengdu, China

  53. JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization

    Jun 9, 2026Ge Shi, Jun Yin, Donglin Xie +3Jailbreak AttacksPrompt Engineering

    University of California, Davis · The Renmin University of China · Independent Researcher +3

  54. Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

    Jun 8, 2026Xiaofeng Lin, Yukai Yang, Daniel Guo +3Jailbreak AttacksLanguage-Model Agents

    University of California, Los Angeles, USA · 2Computer Science and Engineering Department, Texas A&M University, USA · 3Cisco, USA +1

  55. MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

    Jun 5, 2026Rishabh Makwana, Mamta, Deeksha Varshney +1Multilingual SafetyLarge Language Model Jailbreaks

    Dwarkadas Jivanlal Sanghvi College of Engineering, Mumbai, India · King’s College London, London, UK · Indian Institute of Technology Jodhpur, Jodhpur, India

  56. Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

    Jun 4, 2026Minseok Choi, Seungbin Yang, Dongjin Kim +5Large Language Model SafetyJailbreak Attacks

    ♡KAIST AI · ♣Financial Tech Lab, KakaoBank Corp

  57. Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack

    Jun 4, 2026Long P. Hoang, Hai V. Le, Shaoyang Xu +2Large Language Model SafetySafety Alignment

    Singapore University of Technology and Design · Nanyang Technological University

  58. SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

    Jun 4, 2026Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim +2Large Language Model JailbreaksJailbreak Attacks

    Dongguk University-Seoul

  59. GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection

    Jun 4, 2026Paulo Ricardo Ferreira Neves, Edson Rodrigues da Cruz Filho, Paulo Henrique Eleuterio Falsetti +7Prompt-Injection DetectorsJailbreak Attacks

    Quickium Technology Ltd. – Piracicaba, São Paulo · Federal Institute of Education, Science and Technology of São Paulo (IFSP) – Piracicaba Campus – São Paulo · Federal University of São Carlos (UFSCar) – Sorocaba Campus – São Paulo

  60. Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction Subgenres

    Jun 3, 2026Zhongze Luo, Ruihe Shi, Zhenshuai Yin +3Large Language Model JailbreaksJailbreak Attacks

    School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen) · School of Microelectronics, Xi’an Jiaotong University · 2The Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen) +1