Beware the Black-Box: On the Robustness of Recent Defenses to Adversarial Examples

Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analyses of these defenses to include adaptive black-box adversarie...

Descripción completa

Detalles Bibliográficos
Autores principales: Mahmood, Kaleel, Gurevin, Deniz, van Dijk, Marten, Nguyen, Phuoung Ha
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534430/
https://www.ncbi.nlm.nih.gov/pubmed/34682083
http://dx.doi.org/10.3390/e23101359

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534430/
https://www.ncbi.nlm.nih.gov/pubmed/34682083
http://dx.doi.org/10.3390/e23101359

Ejemplares similares