Cargando…

Adversarial attack on deep learning-based dermatoscopic image recognition systems: Risk of misdiagnosis due to undetectable image perturbations

Deep learning algorithms have shown excellent performances in the field of medical image recognition, and practical applications have been made in several medical domains. Little is known about the feasibility and impact of an undetectable adversarial attacks, which can disrupt an algorithm by modif...

Descripción completa

Detalles Bibliográficos
Autores principales: Allyn, Jérôme, Allou, Nicolas, Vidal, Charles, Renou, Amélie, Ferdynus, Cyril
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Lippincott Williams & Wilkins 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7738012/
https://www.ncbi.nlm.nih.gov/pubmed/33327315
http://dx.doi.org/10.1097/MD.0000000000023568