Insider Attacks in Multi-Agent LLM Consensus Systems

Xiaolin Sun, Zixuan Liu, Yibin Hu, Zizhan Zheng

Abstract

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange messages and update decisions to reach a shared outcome. However, most existing multi-agent LLM frameworks assume that all participating agents are aligned with the system objective. In practice, a malicious insider may participate as a legitimate member of the

Categories

Cite This Resource

@article{llmsec202600079,
  title = {Insider Attacks in Multi-Agent LLM Consensus Systems},
  author = {Xiaolin Sun and Zixuan Liu and Yibin Hu and Zizhan Zheng},
  year = {2026},
  url = {https://arxiv.org/abs/2605.08268},
}