AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915375591981056 |
|---|---|
| author | Mao, Junyuan Meng, Fanci Duan, Yifan Yu, Miao Jia, Xiaojun Fang, Junfeng Liang, Yuxuan Wang, Kun Wen, Qingsong |
| author_facet | Mao, Junyuan Meng, Fanci Duan, Yifan Yu, Miao Jia, Xiaojun Fang, Junfeng Liang, Yuxuan Wang, Kun Wen, Qingsong |
| contents | Large Language Model based multi-agent systems are revolutionizing autonomous communication and collaboration, yet they remain vulnerable to security threats like unauthorized access and data breaches. To address this, we introduce AgentSafe, a novel framework that enhances MAS security through hierarchical information management and memory protection. AgentSafe classifies information by security levels, restricting sensitive data access to authorized agents. AgentSafe incorporates two components: ThreatSieve, which secures communication by verifying information authority and preventing impersonation, and HierarCache, an adaptive memory management system that defends against unauthorized access and malicious poisoning, representing the first systematic defense for agent memory. Experiments across various LLMs show that AgentSafe significantly boosts system resilience, achieving defense success rates above 80% under adversarial conditions. Additionally, AgentSafe demonstrates scalability, maintaining robust performance as agent numbers and information complexity grow. Results underscore effectiveness of AgentSafe in securing MAS and its potential for real-world application. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04392 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management Mao, Junyuan Meng, Fanci Duan, Yifan Yu, Miao Jia, Xiaojun Fang, Junfeng Liang, Yuxuan Wang, Kun Wen, Qingsong Artificial Intelligence Large Language Model based multi-agent systems are revolutionizing autonomous communication and collaboration, yet they remain vulnerable to security threats like unauthorized access and data breaches. To address this, we introduce AgentSafe, a novel framework that enhances MAS security through hierarchical information management and memory protection. AgentSafe classifies information by security levels, restricting sensitive data access to authorized agents. AgentSafe incorporates two components: ThreatSieve, which secures communication by verifying information authority and preventing impersonation, and HierarCache, an adaptive memory management system that defends against unauthorized access and malicious poisoning, representing the first systematic defense for agent memory. Experiments across various LLMs show that AgentSafe significantly boosts system resilience, achieving defense success rates above 80% under adversarial conditions. Additionally, AgentSafe demonstrates scalability, maintaining robust performance as agent numbers and information complexity grow. Results underscore effectiveness of AgentSafe in securing MAS and its potential for real-world application. |
| title | AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.04392 |