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...

Full description

Bibliographic Details

Main Authors:	Zifan Wang, Changgen Peng, Xing He, Weijie Tan
Format:	Artigo
Language:	Inglês
Published:	MDPI AG 2023-05-01
Series:	Entropy
Subjects:	Wasserstein distance gradient inversion image reconstruction
Online Access:	https://www.mdpi.com/1099-4300/25/5/810
Tags:	Add Tag No Tags, Be the first to tag this record!