Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined by several critical limitations: they struggle to maintain a coherent progression over long interactions, often losing track of what has been accomplished and what remains to be done; they rely on rigid or pre-defined patterns, and fail to adapt to the LLM's dynamic and unpredictable conversational state. To address these shortcomings, we introduce Mastermind, a multi-turn jailbreak framework that adopts a dynamic and self-improving approach. Mastermind operates in a closed loop of planning, execution, and reflection, enabling it to autonomously build and refine its knowledge of model vulnerabilities through interaction. It employs a hierarchical planning architecture that decouples high-level attack objectives from low-level tactical execution, ensuring long-term focus and coherence. This planning is guided by a knowledge repository that autonomously discovers and refines effective attack patterns by reflecting on interactive experiences. Mastermind leverages this accumulated knowledge to dynamically recombine and adapt attack vectors, dramatically improving both effectiveness and resilience. We conduct comprehensive experiments against state-of-the-art models, including GPT-5 and Claude 3.7 Sonnet. The results demonstrate that Mastermind significantly outperforms existing baselines, achieving substantially higher attack success rates and harmfulness ratings. Moreover, our framework exhibits notable resilience against multiple advanced defense mechanisms.
The State Key Laboratory of Blockchain and Data Security, Zhejiang University(浙江大学区块链与数据安全国家重点实验室);State Key Laboratory of Internet Architecture, Tsinghua University(清华大学互联网架构国家重点实验室);Huazhong University of Science and Technology(华中科技大学);Shanghai AI Laboratory(上海人工智能实验室);East China Normal University(华东师范大学)
SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge
State Key Laboratory of Complex \& Critical Software Environment, Beihang University;College of Science, Mathematics;Technology, Wenzhou-Kean University;360 AI Security Lab;Faculty of Innovation Engineering, Macau University of Science;Hong Kong University of Science;University of Chinese Academy of Sciences
BAIT: Boundary-Guided Disclosure Escalation LLM Jailbreaking via Self-Conditioned Reasoning
The Harbin Institute of Technology(哈尔滨工业大学);The Hong Kong Polytechnic University(香港理工大学);Shenzhen University(深圳大学);Shenzhen Loop Area Institute(深圳河套学院)
Jailbreaking Large Language Models through Iterative Tool-Disguised Attacks via Reinforcement Learning
School of Cyberspace Science and Technology, Beijing Institute of Technology(信息科学与技术学院,北京理工大学);School of Computer Science and Technology, Beijing Institute of Technology(计算机科学与技术学院,北京理工大学);School of Computer Science, University of Auckland(计算机科学学院,奥克兰大学);QAX Security Center, Qi-AnXin Technology Group Inc.(QAX安全中心,启安新科技集团);Qi-AnXin Technology Group Inc.(启安新科技集团);Zhongguancun Laboratory(中关村实验室)
Jailbreaking the Matrix: Nullspace Steering for Controlled Model Subversion
Department of Computer & Information Science & Engineering, University of Florida(佛罗里达大学计算机与信息科学与工程系);School of Computer Science, University of Oklahoma(俄克拉荷马大学计算机科学学院);Computer Science Laboratory, SRI International(SRI国际计算机科学实验室)
Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);People’s Public Security University of China(中国人民公安大学)
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language
Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Pengcheng Laboratory(鹏城实验室);The Chinese University of Hong Kong(香港中文大学);Jilin University(吉林大学);Southwest University(西南大学);University of Electronic Science and Technology of China(电子科技大学);Shenzhen University(深圳大学)
Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking
School of Computer Science and Engineering, Sun Yat-Sen University(中山大学计算机科学与工程学院);Nanyang Technological University(南洋理工大学);Guangdong Province Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室)
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
Georgia Institute of Technology(佐治亚理工学院);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Tsinghua University(清华大学);University of California San Diego(加利福尼亚大学圣迭戈分校);National Taiwan University(台湾大学);IBM Research(IBM研究院)
Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
Zhejiang University(浙江大学);Nanyang Technological University(南洋理工大学);Sun Yat-sen University(中山大学);University of Science and Technology of China(中国科学技术大学);Virginia Tech(弗吉尼亚理工大学)
EVA: Editing for Versatile Alignment against Jailbreaks
ShanghaiTech University(上海科技大学);Sun Yat-sen University(中山大学);State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室);Tsinghua University(清华大学)
Dagger Behind Smile: Fool LLMs with a Happy Ending Story
S-Lab, Nanyang Technological University, Singapore(南洋理工大学新加坡分校S实验室);College of Computing and Data Science, Nanyang Technological University, Singapore(南洋理工大学计算机与数据科学学院)