Dynamic Programming-Based White Box Adversarial Attack for Deep Neural Networks

Recent studies have exposed the vulnerabilities of deep neural networks to some carefully perturbed input data. We propose a novel untargeted white box adversarial attack, the dynamic programming-based sub-pixel score method (SPSM) attack (DPSPSM), which is a variation of the traditional gradient-ba...

Description complète

Détails bibliographiques

Auteurs principaux:	Swati Aggarwal, Anshul Mittal, Sanchit Aggarwal, Anshul Kumar Singh
Format:	Artigo
Langue:	Inglês
Publié:	MDPI AG 2024-07-01
Collection:	AI
Sujets:	adversarial attack strategies deep neural network vulnerabilities convolution neural network dynamic programming-based adversarial attack gradient-based adversarial attacks
Accès en ligne:	https://www.mdpi.com/2673-2688/5/3/59
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!