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...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Swati Aggarwal, Anshul Mittal, Sanchit Aggarwal, Anshul Kumar Singh
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2024-07-01
Serier:	AI
Fag:	adversarial attack strategies deep neural network vulnerabilities convolution neural network dynamic programming-based adversarial attack gradient-based adversarial attacks
Online adgang:	https://www.mdpi.com/2673-2688/5/3/59
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!