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...
محفوظ في:
| المؤلفون الرئيسيون: | , , |
|---|---|
| التنسيق: | Artigo |
| اللغة: | Inglês |
| منشور في: |
MDPI AG
2025-09-01
|
| سلاسل: | Applied Sciences |
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://www.mdpi.com/2076-3417/15/18/10242 |
| الوسوم: |
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|