Hybrid Graph-Transformer Fraud Scoring in Tokenized Card-on-File Ecosystems
Keywords:
fraud detection, heterogeneous graph embedding, temporal transformer, anomaly detection, card-on-fileAbstract
The objective of this paper is to present a hybrid fraud detection method that uses temporal transformers and heterogeneous network embeddings to discover abnormal transaction patterns in tokenised card-on-file (CoF) ecosystems. By including multi-entity connections which includes devices, customer IDs, and tokenised instruments into a uniform graph structure and then simulate their evolution into identifying fraud in milliseconds before transaction clearance.
Downloads
References
J. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec, "Graph Convolutional Neural Networks for Web-Scale Recommender Systems," Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, pp. 974–983, 2018.
W. Hamilton, Z. Ying, and J. Leskovec, "Inductive Representation Learning on Large Graphs," Advances in Neural Information Processing Systems, vol. 30, 2017.
M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, and M. Welling, "Modeling Relational Data with Graph Convolutional Networks," The Semantic Web, pp. 593–607, 2018.
A. Vaswani et al., "Attention Is All You Need," Advances in Neural Information Processing Systems, vol. 30, pp. 5998–6008, 2017.
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, "A Comprehensive Survey on Graph Neural Networks," IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 1, pp. 4–24, 2021.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," NAACL-HLT, pp. 4171–4186, 2019.
Y. Dai, Q. Wu, J. Tang, and J. Pei, "Edge-enhanced Graph Neural Networks for Fraud Detection," Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 15, pp. 13479–13487, 2021.
C. Xu, D. Tao, and C. Xu, "A Survey on Multi-View Learning," Information Fusion, vol. 42, pp. 1–15, 2018.
R. Ying et al., "Graphormer: Transformers for Graphs," Advances in Neural Information Processing Systems, vol. 34, pp. 24981–24994, 2021.
Y. Li, H. Yu, X. Shen, and H. Huang, "A Survey on Graph Neural Networks in Fraud Detection," IEEE Transactions on Neural Networks and Learning Systems, Early Access, 2023.
S. Wu et al., "Tokenized Payments and Fraud Prevention in Digital Commerce," IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 3, pp. 1462–1476, 2022.
K. Zhang, Z. Zheng, P. S. Yu, and Y. Cui, "An Attention-Based Graph Neural Network for Fraud Detection," Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 2457–2460, 2020.
A. Shukla and A. Goel, "Temporal Pattern Analysis Using Transformer Models for Credit Card Fraud Detection," IEEE Access, vol. 9, pp. 142760–142771, 2021.
T. Chen, Z. Xu, and Y. Zhou, "Hybrid Deep Learning Framework for Tokenized Payment Fraud Detection," IEEE Transactions on Information Forensics and Security, vol. 17, pp. 2136–2148, 2022.
L. Sun et al., "Real-Time Anomaly Detection with Graph Attention Networks in Financial Transactions," Proceedings of the 28th ACM SIGKDD Conference, pp. 2560–2568, 2022.
A. Velickovic et al., "Graph Attention Networks," International Conference on Learning Representations (ICLR), 2018.
Y. Kim, S. Jang, and H. Kim, "Dynamic Graph Neural Networks for Fraud Detection in Tokenized Payment Systems," IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 3, pp. 1085–1098, 2022.
J. Li et al., "Federated Learning for Privacy-Preserving Financial Fraud Detection," IEEE Transactions on Big Data, vol. 7, no. 3, pp. 639–651, 2021.
X. Zhang and J. Zhou, "A Survey of Real-Time Fraud Detection in Payment Networks," IEEE Communications Surveys & Tutorials, vol. 23, no. 4, pp. 2161–2186, 2021.
K. Wang et al., "Explainable AI for Fraud Detection in Tokenized Ecosystems: Methods and Challenges," IEEE Transactions on Artificial Intelligence, vol. 3, no. 2, pp. 251–264, 2022.
