Towards fair class-wise robustness: class optimal distribution adversarial training
Abstract Adversarial training has proven to be a highly effective method for improving the robustness of deep neural networks against adversarial attacks. Nonetheless, it has been observed to exhibit a limitation in terms of robust fairness, characterized by a significant disparity in robustness acr...
Sparad:
| Huvudupphov: | , , , , |
|---|---|
| Materialtyp: | Artigo |
| Språk: | Inglês |
| Utgiven: |
Springer
2025-07-01
|
| Serie: | Complex & Intelligent Systems |
| Ämnen: | |
| Länkar: | https://doi.org/10.1007/s40747-025-02038-w |
| Taggar: |
Inga taggar, Lägg till första taggen!
|