Universal adversarial attacks on deep neural networks for medical image classification

Universal adversarial attacks on deep neural networks for medical image classification

Abstract Background Deep neural networks (DNNs) are widely investigated in medical image classification to achieve automated support for clinical diagnosis. It is necessary to evaluate the robustness of medical DNN tasks against adversarial attacks, as high-stake decision-making will be made based o...

Full description

Bibliographic Details
Main Authors: Hokuto Hirano, Akinori Minagi, Kazuhiro Takemoto
Format: Article
Language:English
Published: BMC 2021-01-01
Series:BMC Medical Imaging
Subjects:
Deep neural networks
Medical imaging
Adversarial attacks
Security and privacy
Online Access:https://doi.org/10.1186/s12880-020-00530-y

Internet

https://doi.org/10.1186/s12880-020-00530-y

Similar Items