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...
Tallennettuna:
| Päätekijät: | , , , |
|---|---|
| Aineistotyyppi: | Artigo |
| Kieli: | Inglês |
| Julkaistu: |
MDPI AG
2023-05-01
|
| Sarja: | Entropy |
| Aiheet: | |
| Linkit: | https://www.mdpi.com/1099-4300/25/5/810 |
| Tagit: |
Ei tageja, Lisää ensimmäinen tagi!
|