Improving Transferability of Adversarial Attacks via Frequency-Consistent Regularization
Adversarial examples have revealed the vulnerability of deep neural networks, and their transferability makes black-box attacks particularly concerning. However, perturbations crafted on a surrogate model often do not remain sufficiently effective on unseen target models. In this paper, we revisit t...
Guardat en:
| Autors principals: | , , |
|---|---|
| Format: | Artigo |
| Idioma: | Inglês |
| Publicat: |
MDPI AG
2026-04-01
|
| Col·lecció: | Applied Sciences |
| Matèries: | |
| Accés en línia: | https://www.mdpi.com/2076-3417/16/8/3748 |
| Etiquetes: |
Sense etiquetes, Sigues el primer a etiquetar aquest registre!
|