1 citations · 1 across the 2 of their papers we have counts for
3 papers
Unreasonable Effectiveness of Last Hidden Layer Activations for Adversarial Robustness
Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil
In standard Deep Neural Network (DNN) based classifiers, the general convention is to omit the activation function in the last (output) layer and directly apply the softmax functio…
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil
Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully cra…
Closeness and Uncertainty Aware Adversarial Examples Detection in Adversarial Machine Learning
Omer Faruk Tuna, Ferhat Ozgur Catak, M. Taner Eskil
While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to delibera…