Trade-Offs between Fairness and Privacy in Machine Learning

Citation:

Agarwal S. Trade-Offs between Fairness and Privacy in Machine Learning, in IJCAI 2021 Workshop on AI for Social Good. ; 2021.

Abstract:

The concerns of fairness, and privacy, in machine learning based systems have received a lot of attention in the research community recently, but have primarily been studied in isolation. In this work, we look at cases where we want to satisfy both these properties simultaneously, and find that it may be necessary to make trade-offs between them. We prove a theoretical result to demonstrate this, which considers the issue of compatibility between fair- ness and differential privacy of learning algorithms. In particular, we prove an impossibility theorem which shows that even in simple binary classification settings, one cannot design an accurate learn- ing algorithm that is both ε-differentially private and fair (even approximately).