SecMAS:从设计上保障多智能体系统安全
Securing Multi-Agent Systems by Design
AI 导读
一篇 arXiv 论文提出响应操纵攻击(ReMA),通过基于代理系统的反馈迭代优化恶意响应,对多智能体系统发起无目标与有目标攻击,并证明现有聚合规则对此脆弱。作为防御,作者提出安全聚合规则 SecMAS,利用智能体响应间的语义相似度选出与足够大响应子集最一致的结果,并给出针对两类攻击的理论安全保证。实验显示 SecMAS 能抵御包括自适应变体在内的全部评估攻击,同时保持与现有聚合规则相当的效用。
正文 · 原文
Abstract:Multi-agent systems solve complex tasks by decomposing them into subtasks, delegating the subtasks to agents, and aggregating the agents' responses using an aggregation rule. Malicious agents can manipulate the final solution by providing malicious responses to their assigned subtasks. In this paper, we first propose response manipulation attacks (ReMA), which iteratively optimize malicious responses to maximize attack effectiveness. Specifically, we formulate untargeted and targeted attacks as optimization problems and develop an approach to approximately solve these problems by iteratively refining malicious responses based on feedback from a surrogate multi-agent system. To defend against such attacks, we further propose SecMAS, a secure aggregation rule that leverages the semantic similarities among agent responses to select the response that is most consistent with a sufficiently large subset of the other responses. We theoretically establish security guarantees for SecMAS against both untargeted and targeted attacks. Extensive evaluations demonstrate that existing aggregation rules are vulnerable to ReMA, whereas SecMAS effectively defends against all evaluated attacks, including adaptive variants of ReMA, while maintaining utility comparable to that of existing aggregation rules.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.17883 [cs.CR] |
| (or arXiv:2611.17883v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.17883 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xilong Wang [view email]
[v1]
Fri, 13 Nov 2026 08:22:06 UTC (239 KB)
来源:arXiv cs.AI · arxiv.org