PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System SafetyDownload PDF

Anonymous

16 Feb 2024 (modified: 07 Jun 2024)ACL ARR 2024 February Blind SubmissionReaders: Everyone
Abstract: 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~(\textit{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. Our data and code will be released after the manuscript is accepted.
Paper Type: long
Research Area: Ethics, Bias, and Fairness
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Reproduction study, Data resources, Data analysis
Languages Studied: English
Preprint Status: There is a non-anonymous preprint (URL specified in the next question).
A1: yes
A1 Elaboration For Yes Or No: 6
A2: yes
A2 Elaboration For Yes Or No: 7
A3: yes
A3 Elaboration For Yes Or No: 1
B: yes
B1: yes
B2: yes
B3: n/a
B4: n/a
B5: n/a
B6: yes
B6 Elaboration For Yes Or No: 3
C: yes
C1: n/a
C2: n/a
C3: yes
C4: yes
D: yes
D1: n/a
D2: n/a
D3: n/a
D4: yes
D5: n/a
E: no
E1: n/a
0 Replies

Loading

OpenReview is a long-term project to advance science through improved peer review with legal nonprofit status. We gratefully acknowledge the support of the OpenReview Sponsors. © 2025 OpenReview