Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

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.

[1]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[2]  Philip S. Yu,et al.  Securing Behavior-based Opinion Spam Detection , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[3]  Xiaolong Li,et al.  GeniePath: Graph Neural Networks with Adaptive Receptive Paths , 2018, AAAI.

[4]  Yu Huang,et al.  FdGars: Fraudster Detection via Graph Convolutional Networks in Online App Review System , 2019, WWW.

[5]  Jun Zhou,et al.  A Semi-Supervised Graph Attentive Network for Financial Fraud Detection , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[6]  Tanmoy Chakraborty,et al.  Spotting Collusive Behaviour of Online Fraud Groups in Customer Reviews , 2019, ArXiv.

[7]  James Caverlee,et al.  Wide-Ranging Review Manipulation Attacks: Model, Empirical Study, and Countermeasures , 2019, CIKM.

[8]  Yanfang Ye,et al.  Key Player Identification in Underground Forums over Attributed Heterogeneous Information Network Embedding Framework , 2019, CIKM.

[9]  Chuan Zhou,et al.  Deep Structure Learning for Fraud Detection , 2018, 2018 IEEE International Conference on Data Mining (ICDM).

[10]  Xiaoyu Yang,et al.  Rumor Detection on Social Media with Graph Structured Adversarial Learning , 2020, IJCAI.

[11]  Ekrem Duman,et al.  A cost-sensitive decision tree approach for fraud detection , 2013, Expert Syst. Appl..

[12]  Zhoujun Li,et al.  Label Aware Graph Convolutional Network - Not All Edges Deserve Your Attention , 2019, ArXiv.

[13]  Ruoyu Li,et al.  Adaptive Graph Convolutional Neural Networks , 2018, AAAI.

[14]  Mehryar Mohri,et al.  Multi-armed Bandit Algorithms and Empirical Evaluation , 2005, ECML.

[15]  Hao Chen,et al.  Label-Aware Graph Convolutional Networks , 2020, CIKM.

[16]  Yoshua Bengio,et al.  GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning , 2019, ArXiv.

[17]  Hamed Nilforoshan,et al.  SliceNDice: Mining Suspicious Multi-Attribute Entity Groups with Multi-View Graphs , 2019, 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[18]  Jure Leskovec,et al.  From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews , 2013, WWW.

[19]  Philip S. Yu,et al.  Robust Spammer Detection by Nash Reinforcement Learning , 2020, KDD.

[20]  Zi Huang,et al.  GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection , 2020, SIGIR.

[21]  van den Berg,et al.  UvA-DARE (Digital Academic Modeling Relational Data with Graph Convolutional Networks Modeling Relational Data with Graph Convolutional Networks , 2017 .

[22]  Philip S. Yu,et al.  A Comprehensive Survey on Graph Neural Networks , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[23]  Rajgopal Kannan,et al.  GraphSAINT: Graph Sampling Based Inductive Learning Method , 2019, ICLR.

[24]  Zhi-Hua Zhou,et al.  Exploratory Undersampling for Class-Imbalance Learning , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  Kaiming He,et al.  Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour , 2017, ArXiv.

[26]  Bo Li,et al.  Secure Network Release with Link Privacy , 2020, ArXiv.

[27]  Jie Zhou,et al.  Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View , 2020, AAAI.

[28]  Bryan Hooi,et al.  FlowScope: Spotting Money Laundering Based on Graphs , 2020, AAAI.

[29]  Massimiliano Pontil,et al.  Learning Discrete Structures for Graph Neural Networks , 2019, ICML.

[30]  Yizhou Sun,et al.  Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks , 2019, NeurIPS.

[31]  Udi Weinsberg,et al.  Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks , 2020, WWW.

[32]  Xiaohui Liang,et al.  Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks , 2017, NDSS.

[33]  Arjun Mukherjee,et al.  What Yelp Fake Review Filter Might Be Doing? , 2013, ICWSM.

[34]  Philip S. Yu,et al.  Adversarial Attack and Defense on Graph Data: A Survey , 2018 .

[35]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[36]  Le Song,et al.  Heterogeneous Graph Neural Networks for Malicious Account Detection , 2018, CIKM.

[37]  Christos Faloutsos,et al.  Suspicious Behavior Detection: Current Trends and Future Directions , 2016, IEEE Intelligent Systems.

[38]  Hongzhi Chen,et al.  Measuring and Improving the Use of Graph Information in Graph Neural Networks , 2020, ICLR.

[39]  Jie Chen,et al.  Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics , 2019, ArXiv.

[40]  Chunming Wu,et al.  ASA: Adversary Situation Awareness via Heterogeneous Graph Convolutional Networks , 2020, WWW.

[41]  Jure Leskovec,et al.  Inductive Representation Learning on Large Graphs , 2017, NIPS.

[42]  Philip S. Yu,et al.  Kollector: Detecting Fraudulent Activities on Mobile Devices Using Deep Learning , 2020, IEEE Transactions on Mobile Computing.

[43]  Dong Li,et al.  Spam Review Detection with Graph Convolutional Networks , 2019, CIKM.

[44]  Philip S. Yu,et al.  Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection , 2020, SIGIR.

[45]  Cao Xiao,et al.  FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling , 2018, ICLR.

[46]  Christos Faloutsos,et al.  REV2: Fraudulent User Prediction in Rating Platforms , 2018, WSDM.

[47]  Jiayu Tang,et al.  Financial Defaulter Detection on Online Credit Payment via Multi-view Attributed Heterogeneous Information Network , 2020, WWW.

[48]  Anna Cinzia Squicciarini,et al.  Combating Crowdsourced Review Manipulators: A Neighborhood-Based Approach , 2018, WSDM.

[49]  Selim F. Yilmaz,et al.  Unsupervised Anomaly Detection via Deep Metric Learning with End-to-End Optimization , 2020, ArXiv.

[50]  Tanmoy Chakraborty,et al.  Spotting Collective Behaviour of Online Frauds in Customer Reviews , 2019, IJCAI.

[51]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[52]  Mohammed J. Zaki,et al.  Deep Iterative and Adaptive Learning for Graph Neural Networks , 2019, ArXiv.

[53]  Leman Akoglu,et al.  Collective Opinion Spam Detection: Bridging Review Networks and Metadata , 2015, KDD.

[54]  Danai Koutra,et al.  Graph based anomaly detection and description: a survey , 2014, Data Mining and Knowledge Discovery.