Adversarial example defense based on image reconstruction

The rapid development of deep neural networks (DNN) has promoted the widespread application of image recognition, natural language processing, and autonomous driving. However, DNN is vulnerable to adversarial examples, such as an input sample with imperceptible perturbation which can easily invalida...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Yu(AUST), Xu, Huan, Pei, Chengfei, Yang, Gaoming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2021
Materias:
Artificial Intelligence
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8725667/
https://www.ncbi.nlm.nih.gov/pubmed/35036533
http://dx.doi.org/10.7717/peerj-cs.811

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8725667/
https://www.ncbi.nlm.nih.gov/pubmed/35036533
http://dx.doi.org/10.7717/peerj-cs.811

Ejemplares similares