AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks Through Accuracy Gradient

AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks Through Accuracy Gradient

Adversarial training is exploited to develop a robust Deep Neural Network (DNN) model against the malicious altered data. These attacks may have catastrophic effects on DNN models but are indistinguishable for a human being. For example, an external attack can modify an image adding noises invisible...

Full description

Bibliographic Details
Main Authors: Farzad Nikfam, Alberto Marchisio, Maurizio Martina, Muhammad Shafique
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Deep neural network (DNN)
adversarial training
fast training
hyperparameters
learning rate (LR)
Foolbox
Online Access:https://ieeexplore.ieee.org/document/9915577/

Internet

https://ieeexplore.ieee.org/document/9915577/

Similar Items