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...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Liming Fan, Anis Salwa Mohd Khairuddin, Haichuan Liu, Khairunnisa Binti Hasikin
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	IEEE 2025-01-01
Serie:	IEEE Access
Soggetti:	Adversarial attacks perceptual similarity LPIPS deep neural networks robustness transferability
Accesso online:	https://ieeexplore.ieee.org/document/11078278/
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!