Research on the Application of Security- Weighted Aggregation in Federated Learning for Financial Risk Control
DOI:
https://doi.org/10.61173/nttj5965Keywords:
Federated Learning, Security-Weighted Aggregation, Financial Risk Control, Privacy Preservation, Differential PrivacyAbstract
Federated learning is a privacy-preserving distributed machine learning approach that enables collaborative training by keeping data local and sharing only model parameters. This effectively addresses the challenges of “data silos” and privacy regulations in the field of financial risk control. This paper systematically elaborates on the concepts, development history, architecture, and core mechanisms of federated learning, with a focus on analyzing the principles and implementation of security- weighted aggregation technology, including its reliance on key technologies such as homomorphic encryption, differential privacy, and secure multi-party computation. Besides, this study examines how this technology applies to fintech, outlines common practices, and highlights challenges in technical performance, cross-platform collaboration, and compliance, with possible solutions. The results show that federated learning, using secure aggregation, enables the financial industry to share data and conduct joint risk modeling while staying compliant.
References
[1] Nori, M.K., Yun, S., & Kim, I.-M. (2021). Fast federated learning by balancing communication trade-offs. IEEE Transactions on Communications, 69(8), 5168–5182.
[2] Chaudhary, R. K., Kumar, R., & Saxena, N. (2024). A systematic review on federated learning system: A new paradigm to machine learning. Knowledge and Information Systems, 67(2), 1811–1914.
[3] Konečný J, McMahan H B, Yu F X, et al. Federated learning: Strategies for improving communication efficiency[J]. arXiv preprint arXiv:1610.05492, 2016.
[4] China Academy of Information and Communications Technology (CAICT). (2022). CAICT Report on Federated Learning Application Scenarios. http://www.caict.ac.cn/kxyj/ qwfb/ztbg/202202/P020220222528294962585.pdf
[5] Ma, C., Zhao, H., Zhang, K., Zhang, L., & Huang, H. (2025). A federated supply chain finance risk control method based on personalized differential privacy. Egyptian Informatics Journal, 31, 100704.
[6] Bonawitz K, Ivanov V, Kreuter B, et al. Practical secure aggregation for federated learning on user-held data[J]. arXiv preprint arXiv:1611.04482, 2016.
[7] Wei, L., Chen, C., Zhang, L., Li, M., Chen, Y., & Wang, Q. (2020). Security issues and privacy protection in machine learning. Computer Research and Development, 57(10), 2066- 2085.
[8] Gilad-Bachrach, R., Dowlin, N., Laine, K., Lauter, K., Naehrig, M., & Wernsing, J. (2016). Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In International conference on machine learning, 201-210. Dean&Francis ISSN 2959-6130
[9] Yang, Z., Zhou, M., Yu, H., Sinnott, R. O., & Liu, H. (2023). Efficient and secure federated learning with verifiable weighted average aggregation. IEEE Transactions on Network Science and Engineering, 10(1), 205-222.
[10] Wei, C., Zhao, M., Zhang, Z., et al. (2023 ). Dpmlbench: Holistic evaluation of differentially private machine learning. The 2023 ACM SIGSAC Conference on Computer and Communications Security, 2621-2635.
[11] Rells, J., & Joseph, W. (2025). Federated Learning for Secure Financial Transactions.
[12] Liu, Y., Wang, S., & Nie, X. (2024). Advances, Applications, and Challenges of Federated Learning Technologies in the Financial Domain. Frontiers in Interdisciplinary Applied Science, 1(1), 38-53.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
