Byzantine-robust federated learning over Non-IID data
The malicious attacks of Byzantine nodes in federated learning was studied over the non-independent and identically distributed dataset , and a privacy protection robust gradient aggregation algorithm was proposed.A reference gradient was designed to identify “poor quality” shared gradients in model...
Kaydedildi:
| Asıl Yazarlar: | , , , , , , |
|---|---|
| Materyal Türü: | Artigo |
| Dil: | Chinês |
| Baskı/Yayın Bilgisi: |
Editorial Department of Journal on Communications
2023-06-01
|
| Seri Bilgileri: | Tongxin xuebao |
| Konular: | |
| Online Erişim: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023115/ |
| Etiketler: |
Etiket eklenmemiş, İlk siz ekleyin!
|