Adversarial Defense Method Based on Latent Representation Guidance for Remote Sensing Image Scene Classification

Deep neural networks have made great achievements in remote sensing image analyses; however, previous studies have shown that deep neural networks exhibit incredible vulnerability to adversarial examples, which raises concerns about regional safety and production safety. In this paper, we propose an...

Descripción completa

Detalles Bibliográficos
Autores principales: Da, Qingan, Zhang, Guoyin, Wang, Wenshan, Zhao, Yingnan, Lu, Dan, Li, Sizhao, Lang, Dapeng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10529764/
https://www.ncbi.nlm.nih.gov/pubmed/37761605
http://dx.doi.org/10.3390/e25091306

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10529764/
https://www.ncbi.nlm.nih.gov/pubmed/37761605
http://dx.doi.org/10.3390/e25091306

Ejemplares similares