@inproceedings{yu-etal-2025-netsafe,
    title = "{N}et{S}afe: Exploring the Topological Safety of Multi-agent System",
    author = "Yu, Miao  and
      Wang, Shilong  and
      Zhang, Guibin  and
      Mao, Junyuan  and
      Yin, Chenlong  and
      Liu, Qijiong  and
      Wang, Kun  and
      Wen, Qingsong  and
      Wang, Yang",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.150/",
    pages = "2905--2938",
    ISBN = "979-8-89176-256-5",
    abstract = "Large language models (LLMs) have fueled significant progress in intelligent Multi-agent Systems (MAS), with expanding academic and industrial applications. However, safeguarding these systems from malicious queries receives relatively little attention, while methods for single-agent safety are challenging to transfer. In this paper, we explore MAS safety from a topological perspective, aiming at identifying structural properties that enhance security. To this end, we propose NetSafe framework, unifying diverse MAS workflows via iterative RelCom interactions to enable generalized analysis. We identify several critical phenomena for MAS under attacks (misinformation, bias, and harmful content), termed as $\textit{Agent Hallucination}$, $\textit{Aggregation Safety}$ and $\textit{Security Bottleneck}$. Furthermore, we verify that highly connected and larger systems are more vulnerable to adversarial spread, with task performance in a Star Graph Topology decreasing by 29.7{\%}. In conclusion, our work introduces a new perspective on MAS safety and discovers unreported phenomena, offering insights and posing challenges to the community."
}