TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System

TL;DR

TrendSim is a novel LLM-based multi-agent simulation system designed to model and analyze poisoning attacks on trending topics in social media, aiding in developing effective defense strategies.

Contribution

It introduces a comprehensive simulation environment with human-like agents and attack models to study poisoning attacks on social media trending topics.

Findings

Effective simulation of poisoning attacks demonstrated

Insights into attack impacts on trending topics obtained

Potential defense strategies explored

Abstract

Trending topics have become a significant part of modern social media, attracting users to participate in discussions of breaking events. However, they also bring in a new channel for poisoning attacks, resulting in negative impacts on society. Therefore, it is urgent to study this critical problem and develop effective strategies for defense. In this paper, we propose TrendSim, an LLM-based multi-agent system to simulate trending topics in social media under poisoning attacks. Specifically, we create a simulation environment for trending topics that incorporates a time-aware interaction mechanism, centralized message dissemination, and an interactive system. Moreover, we develop LLM-based human-like agents to simulate users in social media, and propose prototype-based attackers to replicate poisoning attacks. Besides, we evaluate TrendSim from multiple aspects to validate its effectiveness. Based on TrendSim, we conduct simulation experiments to study four critical problems about poisoning attacks on trending topics for social benefit.