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...

Descripció completa

Dades bibliogràfiques

Autors principals:	Jiahuan Zhang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2022-07-01
Col·lecció:	Sensors
Matèries:	adversarial defense adversarial attack feature enhancement feature regularization
Accés en línia:	https://www.mdpi.com/1424-8220/22/14/5431
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!