Papers
arxiv:2510.11246

Collaborative Shadows: Distributed Backdoor Attacks in LLM-Based Multi-Agent Systems

Published on Oct 13
Authors:
,
,
,
,

Abstract

A distributed backdoor attack targeting multi-agent systems achieves high success rates by leveraging agent collaboration without affecting benign tasks.

AI-generated summary

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent backdoor attacks, overlooking the novel attack surfaces introduced by agent collaboration in MAS. To bridge this gap, we present the first Distributed Backdoor Attack tailored to MAS. We decompose the backdoor into multiple distributed attack primitives that are embedded within MAS tools. These primitives remain dormant individually but collectively activate only when agents collaborate in a specific sequence, thereby assembling the full backdoor to execute targeted attacks such as data exfiltration. To fully assess this threat, we introduce a benchmark for multi-role collaborative tasks and a sandboxed framework to evaluate. Extensive experiments demonstrate that our attack achieves an attack success rate exceeding 95% without degrading performance on benign tasks. This work exposes novel backdoor attack surfaces that exploit agent collaboration, underscoring the need to move beyond single-agent protection. Code and benchmark are available at https://github.com/whfeLingYu/Distributed-Backdoor-Attacks-in-MAS.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2510.11246 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2510.11246 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2510.11246 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.