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...

Description complète

Détails bibliographiques

Auteurs principaux:	Zifan Wang, Changgen Peng, Xing He, Weijie Tan
Format:	Artigo
Langue:	Inglês
Publié:	MDPI AG 2023-05-01
Collection:	Entropy
Sujets:	Wasserstein distance gradient inversion image reconstruction
Accès en ligne:	https://www.mdpi.com/1099-4300/25/5/810
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!