MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning 文章

ArXiv CS.AI2026-05-27NEWSen作者: Xuanye Zhang, Yongsen Zheng, Zhuqin Xu, Kaiyu Zhou, Bowen Shen, Haoran Ou, Tianwei Zhang, Kwok-Yan Lam
查看原文 →
关系图谱

MemMorph: Tool Hijacking in LLM Agents via Memory Poisoning · 相关技术

相关技术

ODE远程代码执行（RCE）研究法辛烷值divide-and-conquer partitioningToolsTEEStraight-Through EstimatorReferring expression comprehension (REC)PromiseParts-of-Speech (POS) tagsPPRNarrative Abstraction BenchmarkMaliLMMLLM agentsICTHISENAEFIDiTCISANNAgentTable