MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures -- A Comprehensive Framework

TL;DR

This paper introduces MASTER, a comprehensive framework for analyzing and improving security in multi-agent systems by exploring roles and topological structures, demonstrating significant attack potential and defense strategies.

Contribution

We propose a novel, automated framework for MAS security analysis that incorporates role and topological information to simulate attacks and develop defenses.

Findings

Role and topological information enhance attack effectiveness.

Scenario-adaptive attack strategies increase destructive potential.

Proposed defenses substantially improve MAS resilience.

Abstract

Large Language Models (LLMs)-based Multi-Agent Systems (MAS) exhibit remarkable problem-solving and task planning capabilities across diverse domains due to their specialized agentic roles and collaborative interactions. However, this also amplifies the severity of security risks under MAS attacks. To address this, we introduce MASTER, a novel security research framework for MAS, focusing on diverse Role configurations and Topological structures across various scenarios. MASTER offers an automated construction process for different MAS setups and an information-flow-based interaction paradigm. To tackle MAS security challenges in varied scenarios, we design a scenario-adaptive, extensible attack strategy utilizing role and topological information, which dynamically allocates targeted, domain-specific attack tasks for collaborative agent execution. Our experiments demonstrate that such an attack, leveraging role and topological information, exhibits significant destructive potential across most models. Additionally, we propose corresponding defense strategies, substantially enhancing MAS resilience across diverse scenarios. We anticipate that our framework and findings will provide valuable insights for future research into MAS security challenges.