Privacy-Preserving Machine Learning Techniques

Thesis Abstract

Privacy-preserving machine learning techniques aim to enable the training and deployment of machine learning models while protecting sensitive data. This project will investigate various privacy-preserving methods, including federated learning, differential privacy, and secure multi-party computation. The project will focus on evaluating the trade-offs between privacy and model accuracy, as well as the practical considerations for implementing privacy-preserving machine learning in real-world applications.