Local Methods for Privacy Protection and Impact on Fairness

Abstract

The increasingly pervasive use of big data and machine learning is raising various ethical issues, in particular privacy and fairness. In this talk, I will discuss some frameworks to understand and mitigate the issues, focusing on iterative methods coming from information theory and statistics. In the area of privacy protection, differential privacy (DP) and its variants are the most successful approaches to date. One of the fundamental issues of DP is how to reconcile the loss of information that it implies with the need to preserve the utility of the data. In this regard, a useful tool to recover utility is the iterative Bayesian update (IBU), an instance of the expectation-maximization method from statistics. I will show that the IBU, combined with a version of DP called d-\emphprivacy (also known as metric differential privacy ), outperforms the state-of-the-art, which is based on algebraic methods combined with the randomized response mechanism, widely adopted by the Big Tech industry (Google, Apple, Amazon, ...). Then, I will discuss the issue of biased predictions in machine learning, and how DP can affect the level of fairness and accuracy of the trained model. Finally, I will show that the IBU can be applied also in this domain to ensure fairer treatment of disadvantaged groups and reconcile fairness and accuracy.