Privacy-Preserving Techniques in Credit Risk Assessment: A Comparative Analysis of Differential Privacy, Federated Learning, and Homomorphic Encryption
Keywords:
Privacy-preserving computation, Credit risk assessment, Differential privacy, Federated learning, Homomorphic encryptionAbstract
The proliferation of machine learning in financial services has intensified concerns regarding consumer data privacy during credit risk assessment. This paper presents a comparative study of three privacy-preserving paradigms relevant to credit risk assessment: differential privacy, federated learning, and homomorphic encryption. Through empirical evaluation on a large-scale, representative credit dataset across multiple privacy-preserving configurations, we examine the privacy-utility trade-offs inherent in each approach. Our experimental framework assesses prediction accuracy, computational overhead, and privacy guarantees across multiple configurations. Results demonstrate that differential privacy with epsilon=8.65 achieves a balanced privacy-utility tradeoff with competitive discriminative performance, while homomorphic encryption preserves near-baseline predictive performance during encrypted inference. Federated learning enables collaborative model training across institutions without sharing raw data. The analysis reveals that privacy parameter selection critically impacts model utility, with differential privacy offering quantifiable privacy budgets and homomorphic encryption providing cryptographic security guarantees. These findings provide actionable guidance for financial institutions navigating regulatory compliance requirements while maintaining effective risk management capabilities.References
1. C. Dwork and A. Roth, "The algorithmic foundations of differential privacy," Foundations and Trends in Theoretical Computer Science, vol. 9, no. 3-4, pp. 211-407, 2014.
2. H. He, Z. Wang, H. Jain, C. Jiang, and S. Yang, "A privacy-preserving decentralized credit scoring method based on multi-party information," Decision Support Systems, vol. 166, p. 113910, 2023. Available: https://doi.org/10.1016/j.dss.2022.113910.
3. M. A. Gaikwad, V. H. Satonkar, A. G. Mohod, R. R. Jha, R. M. Giradkar, and S. Rani, "Homomorphic encryption and secure multi-party computation: Mathematical tools for privacy-preserving data analysis in the cloud," Panamerican Mathematical Journal, vol. 33, no. 2, pp. 45-62, 2023.
4. Y. Li, Y. Wang, K. Xu, P. Chen, and M. Zhang, "The effects of data imbalance under a federated learning setting for credit risk assessment," arXiv preprint, arXiv:2401.07234, 2024.
5. Z. Wang, J. Xiao, L. Wang, and J. Yao, "A novel federated learning approach with knowledge transfer for credit scoring," Decision Support Systems, vol. 177, p. 114084, 2024. Available: https://doi.org/10.1016/j.dss.2023.114084.
6. R. Aziz, S. Banerjee, S. Bouzefrane, and T. Le Vinh, "Exploring homomorphic encryption and differential privacy techniques towards secure federated learning paradigm," Future Internet, vol. 15, no. 9, p. 310, 2023.
7. R. T. Potla, "Privacy-preserving synthetic data generation in financial services: Implementing differential privacy in AI-driven data synthesis for regulatory compliance," Journal of Artificial Intelligence Research, pp. 151-174, 2022.
8. P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, et al., "Advances and open problems in federated learning," Foundations and Trends in Machine Learning, vol. 14, no. 1-2, pp. 1-210, 2021.
9. D. Djolev, M. Lazarova, and O. Nakov, "Federated learning for credit scoring model using blockchain," in Optimization, Learning Algorithms and Applications, A. I. Pereira et al., Eds. Springer, 2024, pp. 105-118.
10. V. S. Naresh and D. Ayyappa, "Privacy-preserving federated credit risk models: Evaluating differential privacy and homomorphic encryption techniques," Scientific Reports, vol. 16, p. 4379, 2026. Available: https://doi.org/10.1038/s41598-025-34536-9.
11. A. Oualid, Y. Maleh, and L. Moumoun, "Federated learning techniques applied to credit risk management: A systematic literature review," EDPACS, vol. 68, no. 3, pp. 1-22, 2023.
12. F. Yang, M. Z. Abedin, and P. Hajek, "An explainable federated learning and blockchain-based secure credit modeling method," European Journal of Operational Research, vol. 317, no. 2, pp. 449-467, 2024.
13. J. Chen, D. H. Estrada, and H. Guan, "Bank credit default risk assessment model based on federated learning," Informatica, vol. 50, no. 6, 2026. Available: https://doi.org/10.31449/inf.v50i6.12533.
14. H. Bao, M. Yuan, H. Deng, J. Xu, and Y. Zhao, "Secure multiparty computation protocol based on homomorphic encryption and its application in blockchain," Heliyon, vol. 10, no. 14, p. e34458, 2024. Available: https://doi.org/10.1016/j.heliyon.2024.e34458.
15. X. Kuang, C. Ma, and Y. Ren, "Enabling privacy-preserving and distributed intelligent credit scoring by zero-knowledge proof and functional encryption," Peer-to-Peer Networking and Applications, vol. 18, pp. 1963-4, 2025.
