PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
This addresses safety concerns for multi-agent systems in AI, but it is incremental as it applies psychological concepts to a known problem.
The paper tackles safety risks in multi-agent systems enhanced with Large Language Models by exploring agent psychology, revealing that dark psychological states lead to dangerous behaviors, and proposes the PsySafe framework for attack, defense, and evaluation, with experiments showing phenomena like collective dangerous behaviors and self-reflection.
Multi-agent systems, when enhanced with Large Language Models (LLMs), exhibit profound capabilities in collective intelligence. However, the potential misuse of this intelligence for malicious purposes presents significant risks. To date, comprehensive research on the safety issues associated with multi-agent systems remains limited. In this paper, we explore these concerns through the innovative lens of agent psychology, revealing that the dark psychological states of agents constitute a significant threat to safety. To tackle these concerns, we propose a comprehensive framework (PsySafe) grounded in agent psychology, focusing on three key areas: firstly, identifying how dark personality traits in agents can lead to risky behaviors; secondly, evaluating the safety of multi-agent systems from the psychological and behavioral perspectives, and thirdly, devising effective strategies to mitigate these risks. Our experiments reveal several intriguing phenomena, such as the collective dangerous behaviors among agents, agents' self-reflection when engaging in dangerous behavior, and the correlation between agents' psychological assessments and dangerous behaviors. We anticipate that our framework and observations will provide valuable insights for further research into the safety of multi-agent systems. We will make our data and code publicly accessible at https://github.com/AI4Good24/PsySafe.