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...
Guardat en:
| Autors principals: | , , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
MDPI AG
2023-05-01
|
| Col·lecció: | Entropy |
| Matèries: | |
| Accés en línia: | https://www.mdpi.com/1099-4300/25/5/810 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|