Browsing by Subject "Adverasarial Examples"
Now showing items 1-1 of 1
-
Increasing Transferability by Imposing Linearity and Perturbation in Intermediate Layer with Diverse Input Patterns
(Dhirubhai Ambani Institute of Information and Communication Technology, 2022)Despite high prediction accuracy, deep neural networks are vulnerable to adversarial attacks, introduced by perturbations that humans may not even perceive. Hence, adversarial examples can mislead the trained networks. As ...