Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916016773136384 |
|---|---|
| author | He, Pengfei Xing, Yue Li, Juanhui Dong, Shen Dai, Zhenwei Tang, Xianfeng Liu, Hui Xu, Han Xiang, Zhen Aggarwal, Charu C. Liu, Hui |
| author_facet | He, Pengfei Xing, Yue Li, Juanhui Dong, Shen Dai, Zhenwei Tang, Xianfeng Liu, Hui Xu, Han Xiang, Zhen Aggarwal, Charu C. Liu, Hui |
| contents | TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working collaboratively, are increasingly deployed in high-stakes applications but face novel security threats due to their complex structures. While single-agent vulnerabilities are well-studied, LLM-MAS introduces unique attack surfaces through inter-agent communication, trust relationships, and tool integration that remain significantly underexplored. We present a systematic framework for vulnerability analysis of LLM-MAS that unifies diverse research. For each type of vulnerability, we define formal threat models grounded in practical attacker capabilities and illustrate them using real-world LLM-MAS applications. This formulation enables rigorous quantification of vulnerability across different architectures and provides a foundation for designing meaningful evaluation benchmarks.
We also identify critical open challenges: (1) developing benchmarks specifically tailored to LLM-MAS vulnerability assessment, (2) considering new potential attacks specific to multi-agent architectures, and (3) implementing trust management systems that can enforce security in LLM-MAS. This research provides essential groundwork for future efforts to enhance LLM-MAS trustworthiness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01245 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS He, Pengfei Xing, Yue Li, Juanhui Dong, Shen Dai, Zhenwei Tang, Xianfeng Liu, Hui Xu, Han Xiang, Zhen Aggarwal, Charu C. Liu, Hui Cryptography and Security TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working collaboratively, are increasingly deployed in high-stakes applications but face novel security threats due to their complex structures. While single-agent vulnerabilities are well-studied, LLM-MAS introduces unique attack surfaces through inter-agent communication, trust relationships, and tool integration that remain significantly underexplored. We present a systematic framework for vulnerability analysis of LLM-MAS that unifies diverse research. For each type of vulnerability, we define formal threat models grounded in practical attacker capabilities and illustrate them using real-world LLM-MAS applications. This formulation enables rigorous quantification of vulnerability across different architectures and provides a foundation for designing meaningful evaluation benchmarks. We also identify critical open challenges: (1) developing benchmarks specifically tailored to LLM-MAS vulnerability assessment, (2) considering new potential attacks specific to multi-agent architectures, and (3) implementing trust management systems that can enforce security in LLM-MAS. This research provides essential groundwork for future efforts to enhance LLM-MAS trustworthiness. |
| title | Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2506.01245 |