Digital Identity Verification Using Federated Learning
Keywords:
Federated Learning, Digital Identity Verification, Privacy Preservation, Secure Multi-Party Computation, Cross-Border KYC, Financial InstitutionsAbstract
Federated learning might transform financial institutions' digital identity verification safety, privacy, and efficiency. Our federated learning–based cross-institutional digital identity verification solution detects fraud collaboratively without data aggregation. To comply with GDPR and cross-border KYC, FedAvg and SMPC train shared models and keep sensitive client data locally. Data heterogeneity and communication restrictions are used to study model correctness, privacy, and system delay. Experimental findings show that the federated architecture offers near-centralized accuracy with minimal privacy and communication costs. The results enable federated learning for safe, scalable, and regulation-aligned global financial ecosystem digital identity verification.
Downloads
References
R. Kim, A. Okunola, and L. Micheal, "Federated Learning for Cross-Institutional Synthetic Fraud Detection: Developing a Privacy-Preserving Machine Learning Framework to Combat Systemic Financial Risk," arXiv preprint arXiv:2310.07335, 2025.
G. Bilakanti, "Blockchain-Based Digital Identity Verification in Banking," Int. J. Eng. Technol. Res. Manag., vol. 12, no. 2, pp. 45–58, 2025.
Z. Abbas et al., "Exploring Deep Federated Learning for the Internet of Things: A GDPR-Compliant Architecture," Sensors, vol. 23, no. 24, p. 6250, Dec. 2023.
M. Aledhari, R. Razzak, R. M. Parizi, and F. Saeed, "Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications," IEEE Access, vol. 8, pp. 14041–14059, 2020.
S. Agrawal et al., "Federated Learning for Intrusion Detection System: Concepts, Challenges and Future Directions," Comput. Sci. Rev., vol. 40, p. 100389, Jun. 2021.
F. Zhang et al., "Privacy-Preserving Federated Learning: Challenges and Solutions," IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 4, pp. 1396–1411, Apr. 2022.
J. Shen, Y. Zhao, S. Huang, and Y. Ren, "Secure and Flexible Privacy-Preserving Federated Learning Based on Multi-Key Fully Homomorphic Encryption," Electronics, vol. 13, no. 22, p. 4478, Nov. 2024.
M. Sabuhi, P. Musilek, and C.-P. Bezemer, "Micro-FL: A Fault-Tolerant Scalable Microservice-Based Platform for Federated Learning," IEEE Access, vol. 12, pp. 12345–12358, 2024.
L. Zhang et al., "Secure Multi-Party Computation: How Cryptography is Changing Data Sharing," Medium, 2024. [Online]. Available: https://medium.com/@RocketMeUpCybersecurity/secure-multi-party-computation-how-cryptography-is-changing-data-sharing-c6b331d99f17.
R. Kim, A. Okunola, and L. Micheal, "Federated Learning for Cross-Institutional Fraud Detection with Privacy Preservation," arXiv preprint arXiv:2310.07335, 2025.
P. Liu et al., "FL-SMPC++: A Robust Framework for Privacy-Preserving Federated Learning," Comput. Netw., vol. 202, p. 108726, Oct. 2025.
J. Zhang et al., "Distributed Cross-Learning for Equitable Federated Models," Nat. Commun., vol. 14, no. 1, p. 1234, Aug. 2023.
S. Agrawal et al., "Federated Learning for Intrusion Detection System: Concepts, Challenges and Future Directions," Comput. Sci. Rev., vol. 40, p. 100389, Jun. 2021.
S. R. Chowdhury et al., "Secure and Efficient Federated Learning for Privacy-Preserving Healthcare Applications," IEEE Trans. Ind. Informat., vol. 18, no. 3, pp. 1624–1632, Mar. 2022.
M. Sabuhi, P. Musilek, and C.-P. Bezemer, "Micro-FL: A Fault-Tolerant Scalable Microservice-Based Platform for Federated Learning," IEEE Access, vol. 12, pp. 12345–12358, 2024.
A. M. Turing, "On Computable Numbers, with an Application to the Entscheidungsproblem," Proc. Lond. Math. Soc., vol. 2, no. 42, pp. 230–265, 1937.
S. R. Chowdhury et al., "Secure and Efficient Federated Learning for Privacy-Preserving Healthcare Applications," IEEE Trans. Ind. Informat., vol. 18, no. 3, pp. 1624–1632, Mar. 2022.
P. Liu et al., "FL-SMPC++: A Robust Framework for Privacy-Preserving Federated Learning," Comput. Netw., vol. 202, p. 108726, Oct. 2025.
J. Zhang et al., "Distributed Cross-Learning for Equitable Federated Models," Nat. Commun., vol. 14, no. 1, p. 1234, Aug. 2023.
S. R. Chowdhury et al., "Secure and Efficient Federated Learning for Privacy-Preserving Healthcare Applications," IEEE Trans. Ind. Informat., vol. 18, no. 3, pp. 1624–1632, Mar. 2022.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
