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...
Uloženo v:
| Hlavní autoři: | , , |
|---|---|
| Médium: | Artigo |
| Jazyk: | Inglês |
| Vydáno: |
MDPI AG
2025-09-01
|
| Edice: | Applied Sciences |
| Témata: | |
| On-line přístup: | https://www.mdpi.com/2076-3417/15/18/10242 |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|