用AI代理模拟社交平台热点被攻击时的演化，助力防御研究。
TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System
- 构建基于大模型的多智能体系统，模拟用户互动与信息传播。
- 引入时间感知机制和中心化传播，还原真实热点演进过程。
- 可研究四类热点攻击问题，适合安全与社会影响研究者。
热门话题已成为现代社交媒体的重要组成部分，吸引用户参与突发事件讨论。然而，它们也成为新型污染攻击的新渠道，对社会造成负面影响。因此，亟需研究该关键问题并发展有效防御策略。本文提出TrendSim，一种基于大模型的多智能体系统，用于在污染攻击下模拟社交媒体中的热点话题。具体而言，我们构建了一个包含时间感知交互机制、中心化信息传播和交互系统的热点话题仿真环境。同时，开发了基于大模型的人类行为模拟代理，以还原社交媒体用户行为，并提出原型驱动的攻击者模型来复现污染攻击。此外，我们从多个维度评估了TrendSim的有效性。基于此系统，我们开展了仿真实验，深入研究了关于热点话题污染攻击的四个关键问题，旨在促进社会福祉。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。