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...
Сохранить в:
| Главные авторы: | , , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
MDPI AG
2023-05-01
|
| Серии: | Entropy |
| Предметы: | |
| Online-ссылка: | https://www.mdpi.com/1099-4300/25/5/810 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|