1
Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents
LLM智能体安全新研究，跨智能体攻击归因方法如何串联异步攻击链路
arXiv:2607.18826v1 Announce Type: cross Abstract: LLM-agent defenses are typically evaluated one session at a time. In deployment, however, attacks ca…