Don't Trust Stubborn Neighbors: A Security Framework for Agentic Networks
Samira Abedini, Sina Mavali, Lea Sch\"onherr, Martin Pawelczyk, Rebekka Burkholz

TL;DR
This paper introduces a theoretical framework based on social opinion models to analyze security vulnerabilities in LLM-based multi-agent systems, demonstrating how malicious agents can manipulate collective outcomes and proposing a trust-adaptive defense mechanism.
Contribution
It applies the Friedkin-Johnsen opinion formation model to LLM-MAS, revealing susceptibility to manipulation and proposing a novel trust-adaptive defense to enhance security.
Findings
A single stubborn agent can dominate MAS dynamics.
Increasing benign agents or stubbornness improves security.
Trust-adaptive defense effectively mitigates manipulation.
Abstract
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 introduces new security risks: malicious or compromised agents can exploit communication channels to propagate misinformation and manipulate collective outcomes. 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 LLM-MAS. Remarkably, this model closely captures LLM-MAS behavior, as we verify in extensive experiments across different network topologies and attack and defense scenarios. Theoretically and empirically, we find that a single highly stubborn and persuasive agent can take over MAS dynamics, underscoring the systems' high…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsOpinion Dynamics and Social Influence · Opportunistic and Delay-Tolerant Networks · Advanced Graph Neural Networks
