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...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Yong Li, Wei Du, Liquan Han, Zhenjian Zhang, Tongtong Liu
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	MDPI AG 2023-11-01
Serie:	Sensors
Soggetti:	differentiated differential privacy federated learning gradient pruning privacy preserving
Accesso online:	https://www.mdpi.com/1424-8220/23/23/9305
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!