Cargando…

Disrupting adversarial transferability in deep neural networks

Adversarial attack transferability is well recognized in deep learning. Previous work has partially explained transferability by recognizing common adversarial subspaces and correlations between decision boundaries, but little is known beyond that. We propose that transferability between seemingly d...

Descripción completa

Detalles Bibliográficos
Autores principales: Wiedeman, Christopher, Wang, Ge
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9122968/
https://www.ncbi.nlm.nih.gov/pubmed/35607626
http://dx.doi.org/10.1016/j.patter.2022.100472