Introduction

As the use of sensitive personal data in machine learning models becomes increasingly prevalent, ensuring data privacy and security is paramount. Private-FHE-fraud-detection addresses these concerns by leveraging advanced techniques such as Privacy-Preserving Machine Learning (PPML) and Fully Homomorphic Encryption (FHE).

Main Objectives

• Secure Predictions: Enable predictions on encrypted data without decryption.

• Data Privacy: Ensure user data remains confidential.

• Scalability: Implement a client-server architecture for efficient requests.

Technologies Used

• PPML

• FHE (via Concrete ML)

• FastAPI for server-client interactions.

• Sphinx for documentation generation.