Regularization Meets Enhanced Multi-Stage Fusion Features: Making CNN More Robust against White-Box Adversarial Attacks

Regularization has become an important method in adversarial defense. However, the existing regularization-based defense methods do not discuss which features in convolutional neural networks (CNN) are more suitable for regularization. Thus, in this paper, we propose a multi-stage feature fusion net...

Descrición completa

Detalles Bibliográficos

Principais autores:	Jiahuan Zhang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Formato:	Artigo
Idioma:	Inglês
Publicado:	MDPI AG 2022-07-01
Series:	Sensors
Assuntos:	adversarial defense adversarial attack feature enhancement feature regularization
Acceso en liña:	https://www.mdpi.com/1424-8220/22/14/5431
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!