LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks primarily manipulate the tool metadata, which is easily detectable by auditing and may lose effectiveness as modern agents increasingly adopt memory modules to refine tool selection policies through accumulated experience. This paper proposes MemMorph, the first attack that bias tool selection by poisoning the agent's long-term memory. Rather than explicitly dictating the tool invocation decision, MemMorph injects a small number of crafted records that are disguised as technical facts, incident reports, and operational policies. These poisoned records reshape the agent's contextual perception and decision-making process, leading it to autonomously infer and select the tool preferred by the attacker. Experiments across 3 benchmarks, 10 agent backbones, and 3 memory-module implementations show that MemMorph achieves up to 85.9% attack success rate with only three injected records, outperforming the strongest baseline by up to 25% while retaining potency under 3 representative defenses. Our findings expose long-term memory as a critical and under-explored attack surface in tool-augmented agents, urging the development of memory-level integrity safeguards.
Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
The Hong Kong Polytechnic University(香港理工大学);University of California, San Diego(加州大学圣地亚哥分校);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));Hong Kong Baptist University(香港 Baptist 大学);PolyU Research Centre for Privacy and Security Technologies in Future Smart Systems(PolyU 未来智能系统隐私与安全技术研究中心)
Towards Security-Auditable LLM Agents: A Unified Graph Representation
Huazhong University of Science and Technology(华中科技大学);Nanyang Technological University(南洋理工大学);Fudan University(复旦大学);Chongqing University of Posts and Telecommunications(重庆邮电大学);Donghua University(东华大学)
CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Nokia Bell Labs(诺基亚贝尔实验室)
Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents
Computer Science Department, Southern Illinois University(索尔坦大学计算机科学系);Computer Science Department, University of Texas(德克萨斯大学计算机科学系);Hanyang University(翰阳大学);The Grainger College of Engineering, Nuclear, Plasma & Radiological Engineering, University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校格雷格尔工程学院)
DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models
Institute of Trustworthy Embodied AI, Fudan University(可信具身AI研究院,复旦大学);Shanghai Key Laboratory of Multimodal Embodied AI(上海多模态具身AI重点实验室);City University of Hong Kong(香港城市大学)
ChemMat-AgentSafetyBench: Evaluating Long-Horizon Attacks and Defenses in Chemistry and Materials Agents
Chinese Academy of Sciences(中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Beijing Wenge Technology Co., Ltd.(北京文格科技有限公司);Liaoning University(辽宁大学)