LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing new risks overlooked by existing benchmarks. To systematically scale safety testing into multi-turn, tool-realistic settings, we propose a principled taxonomy that transforms single-turn harmful tasks into multi-turn attack sequences. Using this taxonomy, we construct MT-AgentRisk (Multi-Turn Agent Risk Benchmark), the first benchmark to evaluate multi-turn tool-using agent safety. Our experiments reveal substantial safety degradation: the Attack Success Rate (ASR) increases by 16% on average across open and closed models in multi-turn settings. To close this gap, we propose ToolShield, a training-free, tool-agnostic, self-exploration defense: when encountering a new tool, the agent autonomously generates test cases, executes them to observe downstream effects, and distills safety experiences for deployment. Experiments show that ToolShield effectively reduces ASR by 30% on average in multi-turn interactions. Our code is available at https://github.com/CHATS-lab/ToolShield.
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)
PreAct-Bench: Benchmarking Predictive Monitoring in LLMs
King’s College London(伦敦国王学院);National University of Singapore(新加坡国立大学);Southern University of Science and Technology(南方科技大学);Thomson Reuters Foundational Research(汤姆森路透基础研究);Imperial College London(伦敦帝国学院);The Alan Turing Institute(艾伦·图灵研究所)
Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
School of EECS, Peking University(电子工程系,北京大学);School of Mathematical Sciences, Peking University(数学系,北京大学);State Key Lab of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University(通用人工智能国家重点实验室,智能科学与技术学校,北京大学);Institute for Artificial Intelligence, Peking University(人工智能研究院,北京大学)
Can't See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs
Renmin University of China(中国人民大学);Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Chinese University of Hong Kong(香港中文大学);Johns Hopkins University(约翰霍普金斯大学);Hong Kong University of Science and Technology(香港科技大学);Tencent(腾讯)
Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
Xiongan AI Institute(雄安人工智能研究院);Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);Shanghai Qi Zhi Institute(上海期智研究院)
SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems
Eindhoven University of Technology(埃因霍温理工大学);Indian Institute of Technology Kharagpur(印度理工学院Khargpur分校);Cisco Research(思科研究);Taras Shevchenko National University of Kyiv(塔拉斯·谢甫琴科基辅国立大学);National Technical University of Ukraine(乌克兰国家技术大学);New York University(纽约大学)
When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs
Google(谷歌公司);University of New South Wales(新南威尔士大学);University of Technology Sydney(悉尼科技大学);Zhejiang University(浙江大学);Australian National University(澳大利亚国立大学)
OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety
College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部);School of New Media and Communication, Tianjin University(天津大学新媒体与传播学院);School of Computer and Artificial Intelligence, Zhengzhou University(郑州大学计算机与人工智能学院)
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China(数据科学学院,香港中文大学(深圳));Tencent AI Lab(腾讯人工智能实验室);The Chinese University of Hong Kong(香港中文大学);Shenzhen Research Institute of Big Data, China(深圳大数据研究院)
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(香港科学与技术大学计算机科学与工程系);Department of Computer Science and Engineering, Southern University of Science and Technology(南方科技大学计算机科学与工程系);Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程系);Platform and Content Group, Tencent(腾讯平台与内容组);Chinese Medicine Guangdong Laboratory(广东中医实验室)
Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback
Southern University of Science and Technology(南方科技大学);University of Science and Technology of China(中国科学技术大学);University of Birmingham(伯明翰大学);Zhejiang University(浙江大学);East China Normal University(华东师范大学);Alibaba Group(阿里巴巴集团)