|国家预印本平台
首页|HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learning

HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learning

HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learning

来源:Arxiv_logoArxiv
英文摘要

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.

Georgios Kaissis、Reihaneh Torkzadehmahani、Reza Nasirigerdeh、Jan Baumbach、Daniel Rueckert、Julian Matschinske

计算技术、计算机技术

Georgios Kaissis,Reihaneh Torkzadehmahani,Reza Nasirigerdeh,Jan Baumbach,Daniel Rueckert,Julian Matschinske.HyFed: A Hybrid Federated Framework for Privacy-preserving Machine Learning[EB/OL].(2021-05-21)[2025-08-18].https://arxiv.org/abs/2105.10545.点此复制

评论