Dynamic Asynchronous Anti Poisoning Federated Deep Learning with Blockchain-Based Reputation-Aware Solutions

As promising privacy-preserving machine learning technology, federated learning enables multiple clients to train the joint global model via sharing model parameters. However, inefficiency and vulnerability to poisoning attacks significantly reduce federated learning performance. To solve the aforem...

Cijeli opis

Bibliografski detalji

Glavni autori:	Zunming Chen, Hongyan Cui, Ensen Wu, Xi Yu
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2022-01-01
Serija:	Sensors
Teme:	federated machine learning security privacy-preserving asynchronous poisoning attack
Online pristup:	https://www.mdpi.com/1424-8220/22/2/684
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!