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...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Zifan, Peng, Changgen, He, Xing, Tan, Weijie
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10217429/
https://www.ncbi.nlm.nih.gov/pubmed/37238565
http://dx.doi.org/10.3390/e25050810

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10217429/
https://www.ncbi.nlm.nih.gov/pubmed/37238565
http://dx.doi.org/10.3390/e25050810

Ejemplares similares