Wasserstein Distance-Based Deep Leakage from Gradients

Federated learning protects the privacy information in the data set by sharing the average gradient. However, “Deep Leakage from Gradient” (DLG) algorithm as a gradient-based feature reconstruction attack can recover privacy training data using gradients shared in federated learning, resulting in pr...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Zifan Wang, Changgen Peng, Xing He, Weijie Tan
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	MDPI AG 2023-05-01
Cyfres:	Entropy
Pynciau:	Wasserstein distance gradient inversion image reconstruction
Mynediad Ar-lein:	https://www.mdpi.com/1099-4300/25/5/810
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!