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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Zeyu, Lian, Jianxun, Ma, Chen, Qu, Yaning, Luo, Ye, Wang, Lei, Li, Rui, Chen, Xu, Lin, Yankai, Wu, Le, Xie, Xing, Wen, Ji-Rong
Format:	Preprint
Published:	2024
Subjects:	Social and Information Networks Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866910747946123264
author	Zhang, Zeyu Lian, Jianxun Ma, Chen Qu, Yaning Luo, Ye Wang, Lei Li, Rui Chen, Xu Lin, Yankai Wu, Le Xie, Xing Wen, Ji-Rong
author_facet	Zhang, Zeyu Lian, Jianxun Ma, Chen Qu, Yaning Luo, Ye Wang, Lei Li, Rui Chen, Xu Lin, Yankai Wu, Le Xie, Xing Wen, Ji-Rong
contents	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.
format	Preprint
id	arxiv_https___arxiv_org_abs_2412_12196
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System Zhang, Zeyu Lian, Jianxun Ma, Chen Qu, Yaning Luo, Ye Wang, Lei Li, Rui Chen, Xu Lin, Yankai Wu, Le Xie, Xing Wen, Ji-Rong Social and Information Networks Artificial Intelligence 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.
title	TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System
topic	Social and Information Networks Artificial Intelligence
url	https://arxiv.org/abs/2412.12196