Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection
This addresses fraud detection in financial scenarios like WeChat Pay, offering a novel method to counter sophisticated camouflage strategies, though it is incremental as it builds on existing graph-based techniques.
The paper tackles the problem of fraudsters using adaptive camouflage to evade detection in graph fraud detection, proposing Grad, a relation diffusion-based graph augmentation model that enhances fraud-benign differences and generates auxiliary homophilic relations, resulting in up to 11.10% and 43.95% increases in AUC and AP compared to state-of-the-art methods.
Nowadays, Graph Fraud Detection (GFD) in financial scenarios has become an urgent research topic to protect online payment security. However, as organized crime groups are becoming more professional in real-world scenarios, fraudsters are employing more sophisticated camouflage strategies. Specifically, fraudsters disguise themselves by mimicking the behavioral data collected by platforms, ensuring that their key characteristics are consistent with those of benign users to a high degree, which we call Adaptive Camouflage. Consequently, this narrows the differences in behavioral traits between them and benign users within the platform's database, thereby making current GFD models lose efficiency. To address this problem, we propose a relation diffusion-based graph augmentation model Grad. In detail, Grad leverages a supervised graph contrastive learning module to enhance the fraud-benign difference and employs a guided relation diffusion generator to generate auxiliary homophilic relations from scratch. Based on these, weak fraudulent signals would be enhanced during the aggregation process, thus being obvious enough to be captured. Extensive experiments have been conducted on two real-world datasets provided by WeChat Pay, one of the largest online payment platforms with billions of users, and three public datasets. The results show that our proposed model Grad outperforms SOTA methods in both various scenarios, achieving at most 11.10% and 43.95% increases in AUC and AP, respectively. Our code is released at https://github.com/AI4Risk/antifraud and https://github.com/Muyiiiii/WWW25-Grad.