Edge-Driven Federated Learning System for Secure and Scalable Financial Data Sharing With Privacy Protection
DOI:
https://doi.org/10.4108/eetsis.14493Keywords:
Risk-Aware Sharding, Privacy-Constrained Representation Distillation, Verifiable Robust aggregation, Cross-Institutional Risk Control, non-IID LearningAbstract
INTRODUCTION: Cross-institutional collaborative financial risk modeling can improve fraud detection and anti-money laundering performance. However, data sensitivity, institutional isolation, non-IID data distributions, and heterogeneous edge nodes make traditional federated learning difficult in terms of privacy protection, communication efficiency, and robustness. OBJECTIVES: This paper aims to develop an edge-driven federated learning framework for secure cross-institutional financial risk modeling, enabling collaborative learning without sharing raw financial data. METHODS: The proposed framework integrates risk-relationship-aware dynamic grouping, privacy-constrained representation transmission, robust secure aggregation, and low-dimensional summary consistency checking. By limiting the scope of information exchange and controlling representation sharing, the framework reduces representation deviation and mitigates the influence of abnormal updates. RESULTS: Experiments were conducted on five public or synthetic financial risk datasets. The proposed method achieved the best federated AUPRC on four datasets and was only slightly lower than DSFL on the Elliptic dataset. Under client dropout and malicious-node settings, the method maintained relatively stable AUPRC performance and showed favorable communication efficiency and robustness. CONCLUSION: The results indicate that the proposed edge-driven federated learning framework can support privacy-preserving and robust cross-institutional financial risk modeling. It provides an effective solution for collaborative fraud detection and anti-money laundering under data isolation, heterogeneous edge environments, and adversarial conditions.
References
[1] Asif H, Min S, Wang X, Vaidya J. US-UK PETs prize challenge: Anomaly detection via privacy-enhanced federated learning. IEEE Transactions on Privacy, 2024;1:3-18.
[2] Arora S, Beams A, Chatzigiannis P, Meiser S, Patel K, Raghuraman S, Zamani M. Privacy-preserving financial anomaly detection via federated learning & multi-party computation. Proceedings of the 2024 annual computer security applications conference workshops (ACSAC workshops); Honolulu, HI, USA, 9-10 December 2024. p. 270-279.
[3] Jia N, Qu Z, Ye B, Wang Y, Hu S, Guo S. A comprehensive survey on communication-efficient federated learning in mobile edge environments. IEEE Communications Surveys & Tutorials, 2025;27(6):3710-3741.
[4] Luo L, Zhang C, Yu H, Sun G, Luo S, Dustdar S. Communication-efficient federated learning with adaptive aggregation for heterogeneous client-edge-cloud network. IEEE Transactions on Services Computing, 2024;17(6):3241-3255.
[5] Khan MSI, Gupta A, Seneviratne O, Patterson S. Fed-RD: Privacy-preserving federated learning for financial crime detection. Proceedings of the 2024 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics (CIFEr), Hoboken, NJ, USA, October 22-23, 2024; p. 1-9.
[6] Park DY, Ko IY, Lee TH, Lee J. Federated Gradient Boosting for Financial Fraud Detection: An Empirical Study in the Banking Sector. Proceedings of the 34th ACM International Conference on Information and Knowledge Management; Seoul, Korea, November 10-14, 2025. p. 5089-5093.
[7] Zhou H, Zheng Y, Jia X. Towards robust and privacy-preserving federated learning in edge computing. Computer Networks, 2024;243:110321.
[8] Wang L, Huang M, Zhang Z, Li M, Wang J, Gai K. RaSA: Robust and adaptive secure aggregation for edge-assisted hierarchical federated learning. IEEE Transactions on Information Forensics and Security, 2025;20:4280-4295.
[9] Tang Y, Liang Y. Credit card fraud detection based on federated graph learning. Expert Systems with Applications, 2024;256:124979.
[10] Huang Q, Zhu Y, Liao T, Huang Z. A Federated Learning-Based Approach for Robust and Accurate Financial Fraud Detection. Proceedings of the 2025 International Conference on Artificial Intelligence and Digital Finance; Chengdu, China, June 13-15, 2025. p. 20-24.
[11] Lu H, Wang H. Graph contrastive pre-training for anti-money laundering. International Journal of Computational Intelligence Systems, 2024;17(1):307.
[12] Bakhshinejad N, Nguyen UT, Ghahremani S, Soltani R. A Graph-Based Deep Learning Model for the Anti-Money Laundering Task of Transaction Monitoring. Proceedings of the 16th International Joint Conference on Computational Intelligence (IJCCI), Porto, Portugal, 20-22 November 2024. p. 496-507.
[13] Johannessen F, Jullum M. Finding money launderers using heterogeneous graph neural networks. The Journal of Finance and Data Science, 2025;11:100175.
[14] Chen Y, Zhao C, Xu Y, Nie C, Zhang Y. Deep learning in financial fraud detection: Innovations, challenges, and applications. Data Science and Management, 2026;9(2):100162.
[15] Deprez B, Vanderschueren T, Baesens B, Verdonck T, Verbeke W. Network Analytics for Anti-money Laundering—A Systematic Literature Review and Experimental Evaluation. INFORMS Journal on Data Science, 2025;5(2):81-190.
[16] Yao D, Pan W, Dai Y, Wan Y, Ding X, Yu C, Sun L. FedGKD: Toward heterogeneous federated learning via global knowledge distillation. IEEE Transactions on Computers, 2023;73(1):3-17.
[17] Wu S, Chen J, Nie X, Wang Y, Zhou X, Lu L, Menhaj W. Global prototype distillation for heterogeneous federated learning. Scientific Reports, 2024;14(1):12057.
[18] Luo G, Chen N, He J, Jin B, Zhang Z, Li Y. Privacy-preserving clustering federated learning for non-IID data. Future Generation Computer Systems, 2024;154:384-395.
[19] Hu J, Du J, Wang Z, Pang X, Zhou Y, Sun P, Ren K. Does differential privacy really protect federated learning from gradient leakage attacks? IEEE Transactions on Mobile Computing, 2024;23(12):12635-12649.
[20] Tan Q, Li Q, Zhao Y, Liu Z, Guo X, Xu K. Defending against data reconstruction attacks in federated learning: An information theory approach. Proceedings of the 33rd USENIX security symposium (USENIX Security 24), Philadelphia, PA, USA, August 14–16, 2024. p. 325-342.
[21] Chen L, Zhang W, Dong C, Zhao D, Zeng X, Qiao S, Tan CW. Fedtkd: A trustworthy heterogeneous federated learning based on adaptive knowledge distillation. Entropy, 2024;26(1):96.
[22] Shao J, Wu F, Zhang J. Selective knowledge sharing for privacy-preserving federated distillation without a good teacher. Nature Communications, 2024;15(1):349.
[23] Wang R, Xiong L, Geng J, Xie C, Li R. An effective and verifiable secure aggregation scheme with privacy-preserving for federated learning. Journal of Systems Architecture, 2025;161:103364.
[24] Ming Y, Wang S, Wang C, Liu H, Deng Y, Zhao Y, Feng J. VCSA: Verifiable and collusion-resistant secure aggregation for federated learning using symmetric homomorphic encryption. Journal of Systems Architecture, 2024;156:103279.
[25] Zhou S, Wang L, Chen L, Wang Y, Yuan K. Group verifiable secure aggregate federated learning based on secret sharing. Scientific Reports, 2025;15(1):9712.
[26] Mai P, Yan R, Pang Y. Rflpa: A robust federated learning framework against poisoning attacks with secure aggregation. Advances in Neural Information Processing Systems, 2024;37:104329-104356.
[27] Yang H, Gu D, He J. A robust and efficient federated learning algorithm against adaptive model poisoning attacks. IEEE Internet of Things Journal, 2024;11(9):16289-16302.
[28] Wei K, Li J, Ding M, Ma C, Jeon YS, Poor HV. Covert model poisoning against federated learning: Algorithm design and optimization. IEEE Transactions on Dependable and Secure Computing, 2023;21(3):1196-1209.
[29] Reddy VVK, Reddy RVK, Munaga MSK, Karnam B, Maddila SK, Kolli CS. Deep learning-based credit card fraud detection in federated learning. Expert Systems with Applications, 2024;255:124493.
[30] Shadrooh S, Nørvåg K. SMoTeF: Smurf money laundering detection using temporal order and flow analysis: S. Shadrooh and K. Nørvåg. Applied Intelligence, 2024;54(15):7461-7478.
[31] Ye R, Xu M, Wang J, Xu C, Chen S, Wang Y. Feddisco: Federated learning with discrepancy-aware collaboration. Proceedings of the 40th International Conference on Machine Learning; Honolulu, Hawaii, USA, July 23-29, 2023. JMLR.org. p. 39879-39902.
[32] Noorbakhsh SL, Zhang B, Hong Y, Wang B. Inf2Guard: An Information-Theoretic framework for learning Privacy-Preserving representations against inference attacks. Proceedings of the 33rd USENIX Conference on Security Symposium; Philadelphia, PA, USA, August 14-16, 2024. Berkeley: USENIX Association, USA. 2024. p. 2405-2422.
[33] Ni L, Gong X, Li J, Tang Y, Luan Z, Zhang J. rfedfw: Secure and trustable aggregation scheme for byzantine-robust federated learning in internet of things. Information Sciences, 2024;653:119784.
[34] Guan M, Bao H, Li Z, Pan H, Huang C, Dai HN. SAMFL: Secure Aggregation Mechanism for Federated Learning with Byzantine-robustness by functional encryption. Journal of Systems Architecture, 2024;157:103304.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Wanlin Zhang
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
