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...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Zifan Wang, Changgen Peng, Xing He, Weijie Tan
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	MDPI AG 2023-05-01
Цуврал:	Entropy
Нөхцлүүд:	Wasserstein distance gradient inversion image reconstruction
Онлайн хандалт:	https://www.mdpi.com/1099-4300/25/5/810
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!