Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition

Adversarial Attack and Defence through Adversarial Training and Feature Fusion for Diabetic Retinopathy Recognition

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created exa...

Full description

Bibliographic Details
Main Authors: Sheeba Lal, Saeed Ur Rehman, Jamal Hussain Shah, Talha Meraj, Hafiz Tayyab Rauf, Robertas Damaševičius, Mazin Abed Mohammed, Karrar Hameed Abdulkareem
Format: Article
Language:English
Published: MDPI AG 2021-06-01
Series:Sensors
Subjects:
diabetic retinopathy
adversarial attack
speckle-noise attack
adversarial training
feature fusion
deep learning
Online Access:https://www.mdpi.com/1424-8220/21/11/3922

Internet

https://www.mdpi.com/1424-8220/21/11/3922

Similar Items