A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy

There are several unsolved problems in federated learning, such as the security concerns and communication costs associated with it. Differential privacy (DP) offers effective privacy protection by introducing noise to parameters based on rigorous privacy definitions. However, excessive noise additi...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Yong Li, Wei Du, Liquan Han, Zhenjian Zhang, Tongtong Liu
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2023-11-01
coleção:	Sensors
Assuntos:	differentiated differential privacy federated learning gradient pruning privacy preserving
Acesso em linha:	https://www.mdpi.com/1424-8220/23/23/9305
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!