LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
University of Central Florida(中央佛罗里达大学);University of Maryland, College Park(马里兰大学 College Park 分校);Princeton University(普林斯顿大学);Capital One(Capital One 公司)
James Beetham, Souradip Chakraborty, Mengdi Wang, Furong Huang, Amrit Singh Bedi, Mubarak Shah
越狱攻击通过精心构造的提示词诱发有害输出,暴露了安全对齐大语言模型的脆弱性。现有方法依赖离散优化或训练对抗性生成器,但速度慢、计算密集且往往不切实际。我们认为这些低效源于对问题的错误刻画。相反,我们将越狱重新定义为推理时失对齐,并提出 LIAR(Leveraging Inference-time misAlignment to jailbReak,利用推理时失对齐进行越狱),这是一种快速、黑盒、Best-of-N 采样攻击,无需训练。LIAR 达到了与最先进方法相当的成功率,同时将困惑度降低 10 倍,并将攻击时间(Time-to-Attack)从数小时缩短至数秒。我们还引入了一个理论上的“防越狱安全网”指标,用于量化安全对齐强度,并推导出次优性界限。我们的工作为评估大语言模型鲁棒性和推进对齐研究提供了一个简单而有效的工具。
英文摘要:
Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or trained adversarial generators, but are slow, compute-intensive, and often impractical. We argue that these inefficiencies stem from a mischaracterization of the problem. Instead, we frame jailbreaks as inference-time misalignment and introduce LIAR (Leveraging Inference-time misAlignment to jailbReak), a fast, black-box, best-of-$N$ sampling attack requiring no training. LIAR matches state-of-the-art success rates while reducing perplexity by $10\times$ and Time-to-Attack from hours to seconds. We also introduce a theoretical "safety net against jailbreaks" metric to quantify safety alignment strength and derive suboptimality bounds. Our work offers a simple yet effective tool for evaluating LLM robustness and advancing alignment research.
xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shenzhen University of Advanced Technology(深圳理工大学);WUST(武汉科技大学);HITSZ(哈尔滨工业大学(深圳));School of Biomedical Engineering, UNSW Sydney(新南威尔士大学悉尼分校生物医学工程学院)
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
Lab of Artificial Intelligence for Education, East China Normal University, Shanghai 200062, China(教育人工智能实验室,东华大学,上海200062,中国);Shanghai Institute of Artificial Intelligence for Education, East China Normal University, Shanghai 200062, China(教育人工智能研究所,东华大学,上海200062,中国);School of Computer Science and Technology, East China Normal University, Shanghai 200062, China(计算机科学与技术学院,东华大学,上海200062,中国)
ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models
iFLYTEK Security Laboratory(iFLYTEK安全实验室);Anhui SparkShield Intelligent Technology Co., Ltd.(安徽SparkShield智能科技有限公司);Peking University(北京大学);School of Automation, University of Electronic Science and Technology of China(电子科技大学自动化学院);Northwest University(西北大学);University of New South Wales(新南威尔士大学);National Computer Network Emergency Response Technical Team/Coordination Center of China(中国国家计算机网络应急技术处置协调中心)
From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
School of Information Sciences University of Illinois at Urbana-Champaign(信息科学学院伊利诺伊大学厄巴纳-香槟分校);Computer Science and Engineering HKUST(计算机科学与工程香港科技大学);Computer Science Department University of California, Los Angeles(计算机科学系加州大学洛杉矶分校);Research Scientist, Intel Labs(英特尔实验室研究员);School of Information Sciences University of Illinois Urbana-Champaign(信息科学学院伊利诺伊大学厄巴纳-香槟分校)
Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
Beijing University of Posts and Telecommunications(北京邮电大学);Hangzhou Dianzi University(杭州电子科技大学);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Fujian Cancer Hospital(福建癌症医院)
Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs
School of Electronic, Electrical and communication Engineering, UCAS, Beijing.(电子电气与通信工程学院,中国科学院大学,北京);Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, CAS, Beijing.(智能信息处理重点实验室,计算技术研究所,中国科学院,北京);School of Computer Science and Technology, UCAS, Beijing.(计算机科学与技术学院,中国科学院大学,北京);Key Laboratory of Big Data Mining and Knowledge management, UCAS, Beijing(大数据挖掘与知识管理重点实验室,中国科学院大学,北京);Nanyang Technological University, Singapore.(南洋理工大学,新加坡);Shenzhen Campus of Sun Yat-sen University, Shenzhen.(孙中山大学深圳校区,深圳)
The Straight and Narrow: Do LLMs Possess an Internal Moral Path?
School of Future Technology, Dalian University of Technology, China(大连理工大学未来技术学院);School of Computer Science and Technology, Dalian University of Technology, China(大连理工大学计算机科学与技术学院);Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education, China(教育部社会计算与认知智能重点实验室)
Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages
Bangladesh Institute of Governance and Management (BIGM)(孟加拉国治理与管理研究所);Department of Cyber Security Engineering, George Mason University(网络安全工程系,乔治·梅森大学)
Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models
University of Science and Technology of China(中国科学技术大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Institute of High Performance Computing, A*STAR, Singapore(新加坡A*STAR高性能计算研究所)
RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
School of New Media and Communication, Tianjin University(天津大学新媒体与传播学院);College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);AI Lab, China Mobile Communication Group Tianjin Co., Ltd.(中国移动通信集团天津有限公司AI实验室)
ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages
School of Computer Science, Fudan University(复旦大学计算机科学学院);Shanghai Collaborative Innovation Center of Intelligent Visual Computing(上海智能视觉计算协同创新中心);Institute of Modern Languages and Linguistics, Fudan University(复旦大学现代语言与语言学研究所)
JAILJUDGE: A Comprehensive Jailbreak Judge Benchmark with Multi-Agent Enhanced Explanation Evaluation Framework
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Baidu Inc.(百度公司);The Hong Kong University of Science and Technology(香港科技大学);University of Birmingham(伯明翰大学)
Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education(大数据与人工智能交通联合实验室(北京交通大学));School of Computer Science and Technology, Beijing Jiaotong University(计算机科学与技术学院,北京交通大学);Tsinghua University(清华大学)