arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.06807cs.CRcs.AI
收藏

当智能体行为异常时:基于激活的多智能体系统恶意行为检测

When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

Haowen Xu, Xue Tan, Lei Ma, Zhihao Zhang, Chao Wang, Qingze Wang, Ping Chen, Jun Dai, Xiaoyan Sun

AI总结:

针对多智能体系统面临的安全挑战,提出基于激活的框架AcMAS,通过分析智能体激活空间中的推理状态检测隐蔽攻击,不依赖交互图,还能恢复受损智能体功能,在检测隐蔽攻击上显著优于基线方法。

摘要:

基于大语言模型的多智能体系统(MAS)在实现复杂任务有效协作的同时,因智能体和交互层面的漏洞面临关键安全挑战。现有多数MAS安全防御基于语义明确的恶意攻击以及基于图的MAS拓扑和智能体层面交互显式建模。实际中,现实世界攻击语义更隐蔽,且MAS执行通常异步。为此提出基于激活的框架AcMAS,通过分析本地智能体激活空间中的内部推理状态,能以同步鲁棒方式检测隐蔽攻击,不依赖显式交互图。激活分析还为恢复受损智能体功能提供关键信号。综合评估表明,AcMAS在对抗隐蔽攻击时显著优于基于图的基线方法。

英文摘要:

While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels. Most existing MAS security defenses are built upon two core assumptions: semantically-explicit malicious attacks and explicit graph-based modeling of the MAS topology and agent-level interactions. In practice, real-world attacks are becoming more semantically stealthy, while MAS execution is typically asynchronous without the temporal alignment assumed by graph-based propagation models. To address these limitations, we propose AcMAS, an activation-based framework for malicious-behavior detection in MAS. By analyzing internal reasoning states in the activation space of local agents, AcMAS detects even stealthy attacks in a synchronization-robust fashion, without relying on explicit interaction graphs. Moreover, our activation analysis provides critical signals to guide AcMAS in restoring the functionality of compromised agents, rather than the disruptive agent isolation commonly used by the state-of-the-art methods. Comprehensive evaluation demonstrates that AcMAS significantly outperforms graph-based baselines against stealthy attacks, by +0.22 F1 in synchronous settings (0.94 vs. 0.72) and by +0.55 F1 in asynchronous settings (0.93 vs. 0.38), with generalization across diverse open-source LLM backbones, attack intensity, and MAS scale.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑