DIPA: Adversarial Attack on DNNs by Dropping Information and Pixel-Level Attack on Attention

Deep neural networks (DNNs) have shown remarkable performance across a wide range of fields, including image recognition, natural language processing, and speech processing. However, recent studies indicate that DNNs are highly vulnerable to well-crafted adversarial samples, which can cause incorrec...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Jing Liu, Huailin Liu, Pengju Wang, Yang Wu, Keqin Li
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2024-07-01
Colecção:	Information
Assuntos:	adversarial attack attention mechanism high-frequency information pixel-level attack
Acesso em linha:	https://www.mdpi.com/2078-2489/15/7/391
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!