TrinityGuard: A Unified Framework for Safeguarding Multi-Agent Systems
Kai Wang, Biaojie Zeng, Zeming Wei, Chang Jin, Hefeng Zhou, Xiangtian Li, Chao Yang, Jingjing Qu, Xingcheng Xu, Xia Hu

TL;DR
TrinityGuard is a comprehensive, scalable framework designed to evaluate and monitor safety risks in LLM-based multi-agent systems, addressing vulnerabilities, communication threats, and emergent hazards.
Contribution
It introduces a novel three-tier risk taxonomy and a unified monitoring system tailored for diverse MAS structures, grounded in OWASP standards.
Findings
Effective risk detection across multiple MAS types
Real-time alerts enable prompt mitigation
Formal safety metrics support systematic evaluation
Abstract
With the rapid development of LLM-based multi-agent systems (MAS), their significant safety and security concerns have emerged, which introduce novel risks going beyond single agents or LLMs. Despite attempts to address these issues, the existing literature lacks a cohesive safeguarding system specialized for MAS risks. In this work, we introduce TrinityGuard, a comprehensive safety evaluation and monitoring framework for LLM-based MAS, grounded in the OWASP standards. Specifically, TrinityGuard encompasses a three-tier fine-grained risk taxonomy that identifies 20 risk types, covering single-agent vulnerabilities, inter-agent communication threats, and system-level emergent hazards. Designed for scalability across various MAS structures and platforms, TrinityGuard is organized in a trinity manner, involving an MAS abstraction layer that can be adapted to any MAS structures, an…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInformation and Cyber Security · Mobile Agent-Based Network Management · Access Control and Trust
