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...
保存先:
| 主要な著者: | , , , |
|---|---|
| フォーマット: | Artigo |
| 言語: | Inglês |
| 出版事項: |
MDPI AG
2023-05-01
|
| シリーズ: | Entropy |
| 主題: | |
| オンライン･アクセス: | https://www.mdpi.com/1099-4300/25/5/810 |
| タグ: |
タグなし, このレコードへの初めてのタグを付けませんか!
|