SecureGov-Agent: A Governance-Centric Multi-Agent Framework for Privacy-Preserving and Attack-Resilient LLM Agents

Abstract

Large Language Model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse applications, yet they face critical security challenges including backdoor attacks, prompt injection, and privacy leakage. Existing defense mechanisms typically address single threat vectors, lacking a unified governance architecture for comprehensive security. We propose SecureGov-Agent, a governance-centric multi-agent framework that introduces a dedicated Governance Agent responsible

Categories

Framework mappings

Suggested from the entry's categories.

@inproceedings{chen2025securegovagent,
  title = {{SecureGov-Agent: A Governance-Centric Multi-Agent Framework for Privacy-Preserving and Attack-Resilient LLM Agents}},
  author = {Jinyu Chen and Jixiao Yang and Ziyang Zeng and Zixiao Huang and Jinming Li and Yutong Wang},
  year = {2025},
  month = dec,
  booktitle = {Proceedings of the 2025 6th International Conference on Computer Science and Management Technology},
  doi = {10.1145/3795154.3795296},
  url = {https://www.semanticscholar.org/paper/e2e5529df48fe6cf893da483360958b32d829724}
}