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...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Yong Li, Wei Du, Liquan Han, Zhenjian Zhang, Tongtong Liu
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2023-11-01
Serier:	Sensors
Fag:	differentiated differential privacy federated learning gradient pruning privacy preserving
Online adgang:	https://www.mdpi.com/1424-8220/23/23/9305
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!