研究人员开发了MESA，一个旨在主动识别和优先考虑多智能体系统（MAS）中最易受攻击的通信通道的新框架。该方法旨在通过关注关键节点来优化有限的安全资源，这些节点如果被破坏，可能会严重影响系统的整体成功。MESA利用图论指标和动态探测的组合，无需先验攻击数据即可对这些关键节点进行排名。在各种MAS场景和LLM上的评估表明，MESA的排名与实际攻击成功率高度相关，使防御者能够比随机分配拦截更多的攻击。 AI
影响 通过主动识别和加强关键通信通道来增强多智能体系统的安全性。
排序理由 该集群描述了一篇详细介绍用于保护多智能体系统的新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.30602v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend …
Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders s…