Boosting Adversarial Transferability Through Adversarial Attack Enhancer
Adversarial attacks against deep learning models achieve high performance in white-box settings but often exhibit low transferability in black-box scenarios, especially against defended models. In this work, we propose Multi-Path Random Restart (MPRR), which initializes multiple restart points with...
Сохранить в:
| Главные авторы: | , , |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
MDPI AG
2025-09-01
|
| Серии: | Applied Sciences |
| Предметы: | |
| Online-ссылка: | https://www.mdpi.com/2076-3417/15/18/10242 |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|