KRT-FUAP: Key Regions Tuned via Flow Field for Facial Universal Adversarial Perturbation
It has been established that convolutional neural networks are susceptible to elaborate tiny universal adversarial perturbations (UAPs) in natural image classification tasks. However, UAP attacks against face recognition systems have not been fully explored. This paper proposes a spatial perturbatio...
Сохранить в:
| Главные авторы: | , , , , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
MDPI AG
2024-06-01
|
| Серии: | Applied Sciences |
| Предметы: | |
| Online-ссылка: | https://www.mdpi.com/2076-3417/14/12/4973 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|