Data Privacy in Machine Learning

Program Description

Through this program, the aim is to develop algorithms that ensure individual privacy without unduly reducing model utility. In the EU, where regulatory scrutiny of data handling and public concern over data rights are growing, and as machine learning relies on increasingly large and sensitive datasets, robust privacy guarantees are essential.

The program is organized around two complementary themes. The first theme develops privacy-preserving learning algorithms, including differential privacy and secure multi-party computation. The work focuses on algorithms that provide formal privacy guarantees while maintaining model utility.

The second theme focuses on data control and removal methods, such as machine unlearning, to allow contributors to withdraw or modify their data without prohibitive computational cost.

The vision is to create a cohesive research community bridging theoretical foundations, system implementation, and empirical evaluation in privacy-preserving machine learning.