Federated Fraud Scoring Models for Privacy-Preserving Transaction Intelligence
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V7I1P155Keywords:
Federated Learning, Fraud Detection, Privacy-Preserving Analytics, Secure Aggregation, Financial Transactions, Differential PrivacyAbstract
Global financial systems face escalating threats from sophisticated fraud schemes, necessitating collaborative transaction intelligence among banks, payment processors, and fintech platforms. However, stringent data protection regulations and jurisdictional privacy laws hinder centralized data sharing. This paper introduces a federated fraud scoring architecture that enables distributed model training and inference without transferring raw transaction data. Leveraging federated learning, secure aggregation protocols, and differential privacy mechanisms, the proposed framework preserves data sovereignty while facilitating collaborative fraud detection. Experimental evaluations on benchmark financial datasets demonstrate that the federated model achieves performance comparable to centralized approaches while ensuring strong privacy guarantees. This architecture supports regulatory-compliant intelligence sharing and scalable fraud prevention across cross-border financial ecosystems.
References
[1] H. Liu, J. Chen, and L. Zhang, “Federated Learning for Financial Fraud Detection: A Privacy-Preserving Approach,” IEEE Trans. Neural Netw. Learn. Syst., vol. 32, no. 12, pp. 5534–5547, Dec. 2021.
[2] A. Vepakomma, O. Gupta, T. Swedish, and R. Raskar, “Split Learning for Health: Distributed Deep Learning Without Sharing Raw Patient Data,” Proc. 36th AAAI Conf. Artif. Intell., pp. 7440–7448, 2022.
[3] P. Kairouz et al., “Advances and Open Problems in Federated Learning,” Found. Trends Mach. Learn., vol. 14, no. 1–2, pp. 1–210, 2021.
[4] T. Li, A. K. Sahu, M. Sanjabi, and V. Smith, “Federated Learning: Challenges, Methods, and Future Directions,” IEEE Signal Process. Mag., vol. 37, no. 3, pp. 50–60, May 2020.
[5] D. Ramachandran and A. Singh, “Privacy-Preserving Fraud Detection Using Secure Multi-Party Computation,” IEEE Trans. Inf. Forensics Secur., vol. 18, pp. 190–202, Jan. 2023.
[6] Y. Wang, R. Yu, and X. He, “A Differentially Private Federated Learning Framework for Credit Card Fraud Detection,” Proc. 2022 IEEE Int. Conf. Big Data, pp. 1912–1921, Dec. 2022.
[7] L. Ma, Q. Liu, and J. Gao, “Federated AUC Optimization for Fraud Detection,” Proc. 2021 NeurIPS, pp. 13735–13745, 2021.
[8] S. Sharma and M. Kotecha, “Cross-Border Transaction Intelligence Using Privacy-Preserving AI,” IEEE Access, vol. 11, pp. 11234–11247, Jan. 2023.
[9] X. Zhou et al., “PPFL: Practical Privacy-Preserving Federated Learning for Financial Services,” IEEE Trans. Dependable Secure Comput., vol. 20, no. 4, pp. 1810–1824, Jul.–Aug. 2023.
[10] B. McMahan and D. Ramage, “Communication-Efficient Federated Learning with Adaptive Gradient Clipping,” Proc. ICML 2021, pp. 6672–6681, 2021.
[11] S. Ghosh, P. Bhat, and R. Chatterjee, “Secure Aggregation in Federated Learning: An Enhanced Protocol with Verifiable Computation,” IEEE Trans. Cloud Comput., vol. 11, no. 2, pp. 582–595, Mar.–Apr. 2023.
[12] A. Mishra and N. Patel, “Fraud Detection in Decentralized Financial Systems using Federated Deep Learning,” Proc. 2024 IEEE Conf. FinTech Comput., pp. 77–86, 2024.
[13] V. Sharma and D. Kumar, “Explainable Federated Learning Models for Banking Fraud Scenarios,” IEEE Trans. Ind. Inform., vol. 21, no. 3, pp. 2009–2021, Mar. 2025.
[14] K. Tan, Y. Liu, and S. Wang, “Secure and Scalable Federated Learning for Financial Risk Analytics,” IEEE Internet Things J., vol. 10, no. 5, pp. 4322–4334, Mar. 2023.
[15] J. He, Z. Lin, and M. Ding, “Federated Learning with Adaptive Personalization for Heterogeneous Transaction Patterns,” Proc. 2023 IEEE Int. Conf. Data Mining (ICDM), pp. 135–144, 2023.
[16] M. Lee and A. Das, “Regulatory-Compliant Federated Systems for Fraud Risk Scoring,” IEEE J. Sel. Areas Commun., vol. 41, no. 2, pp. 512–523, Feb. 2023.
[17] H. Zhang, K. Yu, and D. Zhu, “Privacy-Enhanced Deep Fraud Detection with Homomorphic Encryption,” Proc. 2022 IEEE Symp. Secur. Priv., pp. 98–112, 2022.
[18] T. Wang, F. Liu, and C. Yang, “Efficient Client Selection in Federated Learning for High-Risk Fraud Zones,” Proc. 2024 Int. Conf. Machine Learn. Appl. (ICMLA), pp. 312–321, Dec. 2024.
[19] R. Prakash and S. Verma, “Federated Deep Anomaly Detection for Real-Time Transaction Monitoring,” IEEE Trans. Emerg. Top. Comput. Intell., vol. 9, no. 1, pp. 67–79, Feb. 2025.
[20] D. N. Lopez and F. Salim, “Blockchain-Backed Federated Fraud Detection with Auditable Logs,” IEEE Trans. Eng. Manage., vol. 72, no. 3, pp. 702–713, Aug. 2025.
[21] Padala, S. (2025). Predictive AI in Healthcare Contact Centers: A Multi-Layered Approach to Patient Care Optimization. Journal Of Multidisciplinary, 5(7), 335-341.
