GEN-PAY: Leveraging Generative AI and RAG for Securing Payment Gateways with Fraud Detection Systemsustomer Experience with Progressive Web Apps
DOI:
https://doi.org/10.36676/jrps.v16.i1.45Abstract
In an era marked by rapid digital transformation, securing payment gateways against fraudulent activities is of paramount importance. GEN-PAY introduces a novel approach by integrating generative artificial intelligence with Retrieval-Augmented Generation (RAG) techniques to create an adaptive fraud detection system. This framework leverages generative AI to simulate diverse fraudulent scenarios, thereby enriching training datasets and enabling the detection of subtle, emerging patterns that conventional systems might overlook. Simultaneously, the RAG component retrieves and integrates contextual historical data, enhancing the system’s capability to distinguish legitimate transactions from suspicious ones. The combined methodology elevates both the precision and scalability of fraud detection in dynamic payment environments. Empirical studies demonstrate that GEN-PAY reduces false positives while significantly improving detection rates, thus fostering a secure ecosystem for digital financial transactions. The architecture is designed to evolve continuously with emerging cyber threats, ensuring ongoing protection without compromising transaction efficiency. This paper outlines the integration of generative AI and RAG, detailing the underlying algorithms, system architecture, and the challenges encountered during real-world implementation.
Downloads
References
Abdelhamed, S., Daniels, J., & Zhang, Y. (2015). Deep learning approaches for improving fraud detection in electronic payments. IEEE Transactions on Information Forensics and Security, 10(4), 799–808.
•
Li, L., Meng, Q., & Li, Z. (2016). Secure payment gateway architectures: A comparative study. Computer Standards & Interfaces, 44, 100–108.
•
Nian, R., Zhang, T., & Tay, Y. (2016). Credit card fraud detection using deep learning: A survey. Journal of Financial Crime, 23(4), 772–785.
•
Zhang, C., Chen, F., & Liu, H. (2017). Enhanced fraud detection in online payments using ensemble learning. Expert Systems with Applications, 79, 11–19.
•
West, J., & Bhattacharya, M. (2017). Intelligent financial fraud detection: A comprehensive review. Computers & Security, 70, 47–66.
•
Sahin, Y., Bulkan, S., & Duman, E. (2018). A cost-sensitive decision tree approach for fraud detection. Expert Systems with Applications, 103, 282–292.
•
Jurgovsky, J., Granitzer, M., Ziegler, K., Calabretto, S., Portier, P., He-Guelton, L., & Caelen, O. (2018). Sequence classification for credit-card fraud detection. Expert Systems with Applications, 100, 234–245.
•
Nguyen, T. T., & Duong, A. T. (2019). A generative adversarial approach to credit card fraud detection. IEEE Access, 7, 151073–151083.
•
Poornima, S., & Pushpalatha, M. (2019). A survey on credit card fraud detection using machine learning algorithms. International Journal of Computer Sciences and Engineering, 7(5), 1062–1065.
•
Sinha, A., Pandey, S., & Das, D. (2020). A comparative analysis of supervised machine learning algorithms for payment fraud detection. Information Systems Frontiers, 22(4), 999–1011.
•
Lewis, P., Perez, E., Piktus, A., Petroni, F., Kuttler, H., Lewis, M., Lample, G., & Riedel, S. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), 9452–9463.
•
on Services Computing, 15(6), 3509–3518.
•
Lin, J., Luo, X., & Pan, Y. (2022). Explainable AI for payment fraud detection: Techniques and challenges. ACM Computing Surveys, 54(9), Article 205.
•
Chen, W., Yang, Q., & Xu, B. (2023). Hybrid retrieval-augmented generation for secure payment authentication. IEEE Transactions on Knowledge and Data Engineering, 35(5), 3786–3799.
•
Lee, S., Gupta, N., & Srivastava, S. (2023). Ensemble learning meets large-scale payment fraud detection: A cost-sensitive perspective. Knowledge-Based Systems, 263, 110215.
•
Saleh, M., Alghamdi, S., & Hussein, M. (2024). Adversarial robustness in AI-driven payment gateways: A systematic review. Information Sciences, 646, 1169–1182.
•
Morgan, A., Tran, H., & Zhou, J. (2024). Leveraging retrieval-augmented generative models for adaptive fraud detection in e-commerce. Future Generation Computer Systems, 152, 315–327.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal for Research Publication and Seminar
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.