연구
DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs
arXiv:2603.15661v1 Announce Type: new Abstract: Large Language Modelbased MultiAgent Systems MAS have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent, which behave benignly during routine operation and gradually accumulate...
arXiv:2603.15661v1 Announce Type: new Abstract: Large Language Modelbased MultiAgent Systems MAS have demonstrated remarkable collaborative reasoning capabilities but introduce new attack surfaces, such as the sleeper agent, which behave benignly during routine operation and gradually accumulate trust, only revealing malicious behaviors when specific conditions or triggers are met.
이 콘텐츠는 ArXiv AI 원본 기사의 요약입니다. 전문은 원본 사이트에서 확인해주세요.
원문 기사 보기 →