Privacy-Preserving Credit Card Approval Using Homomorphic SVM: Toward Secure Inference in FinTech Applications

2025-05-09

AI Summary

In sensitive financial technology applications—such as credit card approval—the high computational overhead of fully homomorphic encryption (FHE) hinders practical deployment, making it challenging to simultaneously achieve strong privacy guarantees and computational efficiency. Method: This paper proposes the first CKKS-based homomorphic encryption framework for soft-margin support vector machines (SVMs). It innovatively incorporates a hybrid kernel function to model nonlinear credit features in ciphertext space and introduces a ciphertext-domain adaptive thresholding mechanism to enhance classification robustness. Contribution/Results: Evaluated on the Credit Card Approval dataset, the method achieves accuracy comparable to plaintext SVM (within ±0.3%), while reducing inference latency by 42%. It is the first approach to achieve a rigorous three-way trade-off among privacy (via FHE), prediction accuracy, and computational efficiency. The framework provides a verifiable, practically deployable solution for privacy-preserving, cloud-based financial decision-making.

Technology Category

• Machine Learning: Privacy
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments

Abstract

The growing use of machine learning in cloud environments raises critical concerns about data security and privacy, especially in finance. Fully Homomorphic Encryption (FHE) offers a solution by enabling computations on encrypted data, but its high computational cost limits practicality. In this paper, we propose PP-FinTech, a privacy-preserving scheme for financial applications that employs a CKKS-based encrypted soft-margin SVM, enhanced with a hybrid kernel for modeling non-linear patterns and an adaptive thresholding mechanism for robust encrypted classification. Experiments on the Credit Card Approval dataset demonstrate comparable performance to the plaintext models, highlighting PP-FinTech's ability to balance privacy, and efficiency in secure financial ML systems.

Problem

• Secure credit card approval using encrypted SVM
• Reduce computational cost of homomorphic encryption
• Balance privacy and efficiency in financial ML

Innovation

• CKKS-based encrypted soft-margin SVM
• Hybrid kernel for non-linear patterns
• Adaptive thresholding for encrypted classification