English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-agent systems, augmented with Large Language Models (LLMs), demonstratesignificant capabilities for collective intelligence. However, the potentialmisuse of this intelligence for malicious purposes presents significant risks.To date, comprehensive research on the safety issues associated withmulti-agent systems remains limited. From the perspective of agent psychology,we discover that the dark psychological states of agents can lead to severesafety issues. To address these issues, we propose a comprehensive frameworkgrounded in agent psychology. In our framework, we focus on three aspects:identifying how dark personality traits in agents might lead to riskybehaviors, designing defense strategies to mitigate these risks, and evaluatingthe safety of multi-agent systems from both psychological and behavioralperspectives. Our experiments reveal several intriguing phenomena, such as thecollective dangerous behaviors among agents, agents' propensity forself-reflection when engaging in dangerous behavior, and the correlationbetween agents' psychological assessments and their dangerous behaviors. Weanticipate that our framework and observations will provide valuable insightsfor further research into the safety of multi-agent systems. We will make ourdata and code publicly accessible at https:/github.com/AI4Good24/PsySafe.

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