Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

19 Aug 2020  ·  Yingtong Dou, Zhiwei Liu, Li Sun, Yutong Deng, Hao Peng, Philip S. Yu ·

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 opensource toolbox: https://github.com/safe-graph/DGFraud. The CARE-GNN code and datasets are available at https://github.com/YingtongDou/CARE-GNN.

PDF Abstract

Datasets


Introduced in the Paper:

Yelp-Fraud Amazon-Fraud
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Amazon-Fraud CARE-GNN AUC-ROC 89.73 # 4
Fraud Detection Amazon-Fraud CARE-GNN AUC-ROC 89.73 # 4
Fraud Detection Yelp-Fraud CARE-GNN AUC-ROC 75.70 # 5
Node Classification Yelp-Fraud CARE-GNN AUC-ROC 75.70 # 5

Methods


No methods listed for this paper. Add relevant methods here