PrivFairFL: Privacy-Preserving Group Fairness in Federated Learning
This addresses privacy-preserving fairness for federated learning systems, which is an incremental improvement over existing methods.
The paper tackled the conflict between group fairness and privacy in federated learning by proposing a method that combines secure multiparty computation and differential privacy to train fair models without disclosing sensitive attributes.
Group fairness ensures that the outcome of machine learning (ML) based decision making systems are not biased towards a certain group of people defined by a sensitive attribute such as gender or ethnicity. Achieving group fairness in Federated Learning (FL) is challenging because mitigating bias inherently requires using the sensitive attribute values of all clients, while FL is aimed precisely at protecting privacy by not giving access to the clients' data. As we show in this paper, this conflict between fairness and privacy in FL can be resolved by combining FL with Secure Multiparty Computation (MPC) and Differential Privacy (DP). In doing so, we propose a method for training group-fair ML models in cross-device FL under complete and formal privacy guarantees, without requiring the clients to disclose their sensitive attribute values.