TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems

2026-07-10

AI Summary

Existing datasets are inadequate for supporting multimodal fraud detection research in the metaverse virtual economy, where user behavior, financial transactions, and graph-structured relationships must be jointly modeled. This work addresses this gap by introducing, for the first time, a unified multimodal and multitask benchmark dataset that integrates user behavioral logs, transaction records, and relational graphs within a coherent virtual economic framework, simulating realistic fraudulent and bot-driven activities. Leveraging this dataset, we design and evaluate graph neural networks and machine learning models, establishing reproducible baselines across key tasks including transaction fraud detection, cross-modal node classification, and temporal link prediction. Our contribution lays a foundational groundwork for trustworthy AI, graph mining, and multimodal fraud analysis in metaverse environments.

Abstract

The emergence of metaverse platforms has created virtual economies that introduce new challenges related to fraud, bot activity, and illicit financial behavior. Despite growing interest in trustworthy metaverse analytics, existing datasets typically focus on user behavior, authentication, or financial transactions in isolation, limiting the development and reproducible evaluation of multimodal fraud detection methods. To address this gap, we present TSAI-MetaFraud, a multimodal, multi-task benchmark dataset for fraud analytics in virtual economies. TSAI-MetaFraud integrates behavioral, transactional, and graph-structured information while incorporating realistic fraud and automated bot scenarios. We define benchmark tasks including transaction fraud detection, cross-modal node classification, temporal link prediction, and weakly supervised fraud detection, and provide baseline evaluations using machine learning models and graph neural networks. By jointly capturing behavioral activity, financial interactions, and relational structure within a unified virtual economy, TSAI-MetaFraud provides a benchmark for advancing multimodal learning, graph mining, fraud analytics, and trustworthy AI in emerging metaverse ecosystems.

Problem

• metaverse
• financial fraud
• behavioral risk
• multimodal dataset
• benchmark

Innovation

• multimodal fraud detection
• metaverse ecosystems
• graph neural networks
• benchmark dataset
• behavioral risk analytics