How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference
Key Laboratory of Trustworthy Distributed Computing(可信分布式计算重点实验室);Service Beijing University of Posts(北京邮电大学);Artificial Intelligence Research Institute China Academy of Information(人工智能研究所信息与通信技术 academy)
Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely rely on coarse classifications that focus mainly on harmfulness, leading to substantial overestimation of attack success. To address this problem, we propose FJAR, a fine-grained jailbreak evaluation framework with anchored references. We first categorized jailbreak responses into five fine-grained categories: Rejective, Irrelevant, Unhelpful, Incorrect, and Successful, based on the degree to which the response addresses the malicious intent of the query. This categorization serves as the basis for FJAR. Then, we introduce a novel harmless tree decomposition approach to construct high-quality anchored references by breaking down the original queries. These references guide the evaluator in determining whether the response genuinely fulfills the original query. Extensive experiments demonstrate that FJAR achieves the highest alignment with human judgment and effectively identifies the root causes of jailbreak failures, providing actionable guidance for improving attack strategies.
SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
National Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);University of Liverpool(利物浦大学);City University of Hong Kong(香港城市大学);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院);China Mobile Research Institute(中国移动研究院);China Mobile (Suzhou) Software Technology Co., Ltd(中国移动苏州软件技术有限公司)
Activation-Guided Local Editing for Jailbreaking Attacks
Beihang University(北航);Hangzhou Innovation Institute(杭州创新研究院);HKUST(香港科技大学);South China University of Technology(华南理工大学);Nanyang Technological University(南洋理工大学);Kunming University of Science and Technology(昆明理工大学)
TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
School of Cyber Science and Engineering, Xi’an Jiaotong University(网络安全科学与工程学院,西安交通大学);Singapore Management University(新加坡管理学院);Nanyang Technological University(南洋理工大学)
MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University(武汉大学网络安全学院);School of Cyber Science and Engineering, Tianjin University(天津大学网络安全学院)
Toward Understanding the Transferability of Adversarial Suffixes in Large Language Models
Ludwig-Maximilians-Universität München(慕尼黑莱布尼茨-马克斯大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);Carnegie Mellon University(卡内基梅隆大学);University of Maryland(马里兰大学)
Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory
TMLR Group, Hong Kong Baptist University(香港 Baptist 大学 TMLR 实验组);The University of Texas at Austin(德克萨斯大学奥斯汀分校);Shanghai Jiao Tong University(上海交通大学);Sydney AI Center, The University of Sydney(悉尼大学悉尼人工智能中心)