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...

全面介紹

書目詳細資料

Principais autores:	Zifan Wang, Changgen Peng, Xing He, Weijie Tan
格式:	Artigo
語言:	Inglês
出版:	MDPI AG 2023-05-01
叢編:	Entropy
主題:	Wasserstein distance gradient inversion image reconstruction
在線閱讀:	https://www.mdpi.com/1099-4300/25/5/810
標簽:	添加標簽 沒有標簽, 成為第一個標記此記錄!