arXiv cs.CY· Keyang Chen, Mingxuan Jiang, Zeping Li, Yiwen Zhao, Yifan Wang, Qiuyang Zhang, Shuaicheng Qi, Yicun Liu, Zhixin Li, Sen Liu, Yinan Jing, Guangnan Ye, Hongfeng Chai·· 12 小时前AI 评分38
FraudSociety：首个联合建模信息与资金动态的 LLM 智能体金融欺诈模拟器
FraudSociety: A Generative Agent-Based Society for the Financial-Fraud Economy
AI 导读
FraudSociety 是首个基于 LLM 智能体的模拟器，同时建模信息传播与资金流动两类耦合动态，用于还原金融欺诈在现实中的演化过程。其模拟结果在多项关键统计上与真实欺诈模式吻合，并复现了损失高度集中的现象——前 10% 受害记录占总损失的 81.1%。反欺诈实验显示，最佳个性化干预可将重复支付率从 49.4% 降至 10.9%。
正文
Authors:Keyang Chen, Mingxuan Jiang, Zeping Li, Yiwen Zhao, Yifan Wang, Qiuyang Zhang, Shuaicheng Qi, Yicun Liu, Zhixin Li, Sen Liu, Yinan Jing, Guangnan Ye, Hongfeng Chai
Abstract:Financial fraud caused over \$15.9 billion in losses in the United States in 2025, according to the Federal Trade Commission~\citep{ftc2026databook}. Understanding such large-scale harm requires jointly modeling informational and financial dynamics. Yet existing simulators typically capture only one side of this interaction, leaving a gap in modeling how fraud unfolds in the real world. To bridge this gap, we introduce \textsc{FraudSociety}, the first LLM-agent-based simulator that jointly models these coupled dynamics. It integrates a dynamic social environment for information exposure and communication, persistent financial ledgers that preserve payment and loss histories, and a Need-Intent-Action architecture for civilian decision making. Fraudsters further adapt their communication and financial actions to individual interaction histories and ledger states, forming a closed feedback loop between the two dynamics. We validate \textsc{FraudSociety} across macro-level outcomes, micro-level behavior, and intervention effects. At the macro level, the simulated fraud outcomes closely match real-world patterns across multiple key statistics. At the micro level, it reproduces strong loss concentration, with the top 10\% of victimization records accounting for 81.1\% of total losses, consistent with Canadian Anti-Fraud Centre statistics~\citep{cafc2025annual}. Counter-fraud experiments further reveal variation across intervention strategies, with the best-performing personalized intervention reducing the repeat-payment rate from 49.4\% to 10.9\%. These results establish \textsc{FraudSociety} as both a high-fidelity simulator and a scalable testbed for evaluating anti-fraud strategies under diverse intervention conditions, thereby advancing research on financial fraud and its prevention.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY) |
| Cite as: | arXiv:2610.33536 [cs.AI] |
| (or arXiv:2610.33536v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33536 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mingxuan Jiang [view email]
[v1]
Sat, 24 Oct 2026 08:26:22 UTC (2,613 KB)
来源：arXiv cs.CY · arxiv.org