AI RESEARCH
Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
arXiv CS.AI
•
ArXi:2603.15809v1 Announce Type: cross Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solving. Yet, their interactive nature In this paper, we study how such manipulation can arise and spread by borrowing the Friedkin-Johnsen opinion formation model from social sciences to propose a general theoretical framework to study