Toward Robustness and Privacy in Federated Learning: Experimenting with Local and Central Differential Privacy

Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local and only exchanging model updates. Alas, recent work highlighted several privacy and robustness weaknesses in FL, presenting, respectively, membership/property inference and backdoor attacks. In this paper, we investigate to what extent Differential Privacy (DP) can be used to protect not only privacy but also robustness in FL. We present a first-of-its-kind empirical evaluation of Local and Central Differential Privacy (LDP/CDP) techniques in FL, assessing their feasibility and effectiveness. We show that both DP variants do defend against backdoor attacks, with varying levels of protection and utility, and overall much more effectively than previously proposed defenses. They also mitigate white-box membership inference attacks in FL, and our work is the first to show how effectively; neither, however, provides viable defenses against property inference. Our work also provides a re-usable measurement framework to quantify the trade-offs between robustness/privacy and utility in differentially private FL.