Boosting the Transferability of Adversarial Attacks with Semantic-Invariance and Low-Gradient Replacement
Deepneural networks are highly vulnerable to adversarial examples, which are generated by introducing subtle perturbations to input data to mislead model classification. Currently, transfer-based attacks are prevalent in adversarial example generation and can be categorized into input transformation...
Zapisane w:
| Główni autorzy: | , , , , |
|---|---|
| Format: | Artigo |
| Język: | Inglês |
| Wydane: |
MDPI AG
2026-07-01
|
| Seria: | Mathematics |
| Hasła przedmiotowe: | |
| Dostęp online: | https://www.mdpi.com/2227-7390/14/13/2392 |
| Etykiety: |
Nie ma etykietki, Dołącz pierwszą etykiete!
|
