AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems 文章

ArXiv CS.AI2026-06-16NEWSen作者: Faouzi El Yagoubi, Godwin Badu-Marfo, Ranwa Al Mallah
查看原文 →
关系图谱

AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems · 相关技术

相关技术

large language models