Konu "Loss maximization" için MF - Makale Koleksiyonu | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering listeleme
Toplam kayıt 1, listelenen: 1-1
-
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
(Springer, 2022-03)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, ...