Browsing Department of Electrical and Computer Engineering (TN-IDE) by Journals "Multimedia tools and applications"
Now showing items 1-1 of 1
-
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
(Peer reviewed; Journal article, 2022)Deep neural network (DNN) architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, ...