arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.26154cs.CRcs.AI
收藏

MemMorph:通过记忆投毒实现LLM代理中的工具劫持

MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning

Nanyang Technological University, Singapore(南洋理工大学,新加坡)

Xuanye Zhang, Yongsen Zheng, Zhuqin Xu, Kaiyu Zhou, Bowen Shen, Haoran Ou, Tianwei Zhang, Kwok-Yan Lam

AI总结:

提出MemMorph攻击,通过向长期记忆注入少量伪装记录,诱导LLM代理自主选择攻击者偏好的工具,在多个基准测试中实现高达85.9%的攻击成功率。

摘要:

LLM驱动的代理能够选择外部工具来完成用户任务。然而,攻击者可能破坏这一过程,引导代理使用不当/错误的工具并实施恶意行为。现有攻击主要操纵工具元数据,这容易被审计检测,并且随着现代代理越来越多地采用记忆模块通过积累经验来优化工具选择策略,这些攻击可能失效。本文提出MemMorph,这是首次通过投毒代理的长期记忆来偏置工具选择的攻击。MemMorph不直接指定工具调用决策,而是注入少量伪装成技术事实、事件报告和操作策略的精心构造记录。这些投毒记录重塑了代理的上下文感知和决策过程,使其自主推断并选择攻击者偏好的工具。在3个基准测试、10个代理骨干和3个记忆模块实现上的实验表明,MemMorph仅需注入3条记录即可达到高达85.9%的攻击成功率,在3种代表性防御下仍保持效力,比最强基线高出25%。我们的发现揭示了长期记忆是工具增强代理中一个关键且被忽视的攻击面,敦促开发记忆层面的完整性保障。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑