Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

作     者：Dou, Yingtong Liu, Zhiwei Sun, Li Deng, Yutong Peng, Hao Yu, Philip S. 

作者机构：Department of Computer Science University of Illinois at Chicago United States School of Computer Science Beijing University of Posts and Telecommunications China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2020年

核心收录：

主　　题：Graph neural networks 

摘      要：Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations. However, few prior works have noticed the camouflage behavior of fraudsters, which could hamper the performance of GNN-based fraud detectors during the aggregation process. In this paper, we introduce two types of camouflages based on recent empirical studies, i.e., the feature camouflage and the relation camouflage. Existing GNNs have not addressed these two camouflages, which results in their poor performance in fraud detection problems. Alternatively, we propose a new model named CAmouflage-REsistant GNN (CARE-GNN), to enhance the GNN aggregation process with three unique modules against camouflages. Concretely, we first devise a label-aware similarity measure to find informative neighboring nodes. Then, we leverage reinforcement learning (RL) to find the optimal amounts of neighbors to be selected. Finally, the selected neighbors across different relations are aggregated together. Comprehensive experiments on two real-world fraud datasets demonstrate the effectiveness of the RL algorithm. The proposed CARE-GNN also outperforms state-of-the-art GNNs and GNN-based fraud detectors. We integrate all GNN-based fraud detectors as an open-source toolbox1. The CARE-GNN code and datasets are available at https://***/YingtongDou/CARE-GNN. Copyright © 2020, The Authors. All rights reserved.