From static to adaptive: immune memory-based jailbreak detection for large language models
Beijing University of Posts and Telecommunications(北京邮电大学);Hunan Branch of National Computer Network Emergency Response(国家计算机网络应急技术处理协调中心湖南分中心);Clinical Oncology School of Fujian Medical University(福建医科大学临床肿瘤学院)
Jun Leng, Yu Liu, Litian Zhang, Ruihan Hu, Zhuting Fang, Xi Zhang
Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently, robust detection of such malicious inputs is paramount for ensuring model safety. Traditional detection methods typically rely on external models trained on fixed, large-scale datasets, which often incur significant computational overhead. While recent methods shift toward leveraging internal safety signals of models to enable more lightweight and efficient detection. However, these methods remain inherently static and struggle to adapt to the evolving nature of jailbreak attacks. Drawing inspiration from the biological immune mechanism, we introduce the Immune Memory Adaptive Guard (IMAG) framework. By distilling and encoding safety patterns into a persistent, evolvable memory bank, IMAG enables adaptive generalization to emerging threats. Specifically, the framework orchestrates three synergistic components: Immune Detection, which employs retrieval for high-efficiency interception of known jailbreak attacks; Active Immunity, which performs proactive behavioral simulation to resolve ambiguous unknown queries; Memory Updating, which integrates validated attack patterns back into the memory bank. This closed-loop architecture transitions LLM defense from rigid filtering to autonomous adaptive mitigation. Extensive evaluations across five representative open-source LLMs demonstrate that our method surpasses state-of-the-art (SOTA) baselines, achieving a superior average detection accuracy of 94\% across diverse and complex attack types.
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
University of Maryland(马里兰大学);Indian Institute of Technology Bombay(印度班加罗尔理工学院);Princeton University(普林斯顿大学);University of Colorado Boulder(科罗拉多大学博尔德分校);Capital One(Capital One公司);University of Central Florida(佛罗里达中央大学)
JailbreakOPT: Iterative Jailbreak Prompt Optimization with Macro-Action
University of California, Davis(加州大学戴维斯分校);The Renmin University of China(中国人民大学);Independent Researcher(独立研究员);Nankai University(南开大学);Cornell University(康奈尔大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全全国重点实验室);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术开发区(滨江)区块链与数据安全研究所);Shanghai AI Laboratory(上海人工智能实验室);East China Normal University(华东师范大学)
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
University of California, Los Angeles(加州大学洛杉矶分校);University of Washington(华盛顿大学);Qatar Computing Research Institute(卡塔尔计算研究所);Google(谷歌);Stanford University(斯坦福大学)
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)
East China Normal University(东华大学);Shanghai Innovation Institute(上海创新研究院);University of Southampton(南安普顿大学);Shanghai Jiao Tong University(上海交通大学);Software Engineering Institute, East China Normal University(东华大学软件工程研究院)
Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors
Department of Computing The Hong Kong Polytechnic University Hong Kong SAR, China;Centre for Artificial Intelligence;Robotics Hong Kong Institute of Science \& Innovation Chinese Academy of Sciences Hong Kong SAR, China
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
Peking University(北京大学);University of Wisconsin–Madison(威斯康星大学麦迪逊分校);International Digital Economy Academy(国际数字经济学院);University of California Davis(加州大学戴维斯分校)
Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
Faculty of Data Science, City University of Macau(澳门城市大学数据科学学院);School of Information and Safety Engineering, Zhongnan University of Economics and Law(中南财经政法大学信息与安全工程学院)
Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks
Nanjing University of Science and Technology(南京理工大学);The University of Sydney(悉尼大学);National University of Singapore(新加坡国立大学);University of New South Wales(新南威尔士大学);Nanjing University(南京大学)
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
School of Cyber Science and Technology, University of Science and Technology of China, China(中国科学技术大学信息科学与技术学院);Nanyang Technological University, Singapore(南洋理工大学);Tsinghua University, Beijing, China(清华大学);Beijing Electronic Science and Technology Institute, Beijing, China(北京电子科技研究所)