HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learning
This addresses privacy risks for users in federated learning systems, though it appears incremental as it builds on existing FL methods.
The paper tackles the problem of privacy leakage in federated learning by introducing HyFed, a framework that enhances privacy while preserving model utility, and provides a generic API for developing privacy-preserving federated algorithms with publicly available source code.
Federated learning (FL) enables multiple clients to jointly train a global model under the coordination of a central server. Although FL is a privacy-aware paradigm, where raw data sharing is not required, recent studies have shown that FL might leak the private data of a client through the model parameters shared with the server or the other clients. In this paper, we present the HyFed framework, which enhances the privacy of FL while preserving the utility of the global model. HyFed provides developers with a generic API to develop federated, privacy-preserving algorithms. HyFed supports both simulation and federated operation modes and its source code is publicly available at https://github.com/tum-aimed/hyfed.