QR kód

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...

Celý popis

Uloženo v:
Hlavní autoři: Yunqi Zhang, Wei Chen, Lei Zhao, Liwen Wu, Tong Su
Médium: Artigo
Jazyk:Inglês
Vydáno: MDPI AG 2026-07-01
Edice:Mathematics
Témata:
adversarial examples
deep neural networks
low-gradient
transferable attacks
semantic-invariance
On-line přístup:https://www.mdpi.com/2227-7390/14/13/2392
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky