Perceptual Carlini-Wagner Attack: A Robust and Imperceptible Adversarial Attack Using LPIPS

Adversarial attacks on deep neural networks (DNNs) present significant challenges by exploiting model vulnerabilities using perturbations that are often imperceptible to human observers. Traditional approaches typically constrain perturbations using p-norms, which do not effectively capture human pe...

Popoln opis

Bibliografske podrobnosti

Principais autores:	Liming Fan, Anis Salwa Mohd Khairuddin, Haichuan Liu, Khairunnisa Binti Hasikin
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2025-01-01
Serija:	IEEE Access
Teme:	Adversarial attacks perceptual similarity LPIPS deep neural networks robustness transferability
Online dostop:	https://ieeexplore.ieee.org/document/11078278/
Oznake:	Označite Brez oznak, prvi označite!