paper-with-me

Papers

AgentSafe: Safeguarding Large Language Model-based Multi-agent Systems via Hierarchical Data Management

2025-03-06 · Junyuan Mao, Fanci Meng, Yifan Duan, Miao Yu, Xiaojun Jia, Junfeng Fang, Yuxuan Liang, Kun Wang, Qingsong Wen

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.

📄 PDF Abstract BibTeX arXiv:2503.04392

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingLarge Language ModelManagement

Methods 이 논문이 사용한 방법론

MAS This optimizer mix ADAM and SGD creating the MAS optimizer.

Similar Papers 제목 키워드 기반

OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety

2025-07-08 · Sanidhya Vijayvargiya, Aditya Bharat Soni, Xuhui Zhou, Zora Zhiruo Wang 외

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous e…

AI AgentScheduling

GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling

2025-05-25 · Jialong Zhou, Lichao Wang, Xiao Yang

The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration face critical safety challenges, suc…

DecoderHallucination

SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection

2025-10-17 · Yang Feng, Xudong Pan arxiv

Malicious agents pose significant threats to the reliability and decision-making capabilities of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs). Existing defenses often fall short due to reactive desig…

Contrastive Learning

Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection

2025-12-21 · Junjun Pan, Yixin Liu, Rui Miao, Kaize Ding 외 arxiv

Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical tasks, detecting malicious agents has b…

Graph Anomaly Detection

Multilingual Collaborative Defense for Large Language Models

2025-05-17 · Hongliang Li, Jinan Xu, Gengping Cui, Changhao Guan 외

The robustness and security of large language models (LLMs) has become a prominent research area. One notable vulnerability is the ability to bypass LLM safeguards by translating harmful queries into rare or underreprese…