1
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
系统揭示LLM Agents如何从不安全输入污染可信记忆，首份系统性内存投毒攻防研究
arXiv:2606.04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions a…