Yazar "Tuna, Ömer Faruk" için listeleme
-
BOUN-ISIK participation: an unsupervised approach for the named entity normalization and relation extraction of Bacteria Biotopes
Karadeniz, İlknur; Tuna, Ömer Faruk; Özgu, Arzucan (Association for Computational Linguistics (ACL), 2019-11-04)This paper presents our participation at the Bacteria Biotope Task of the BioNLP Shared Task 2019. Our participation includes two systems for the two subtasks of the Bacteria Biotope Task: the normalization of entities ... -
Closeness and uncertainty aware adversarial examples detection in adversarial machine learning
Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Elsevier Ltd, 2022-07)While deep learning models are thought to be resistant to random perturbations, it has been demonstrated that these architectures are vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These ... -
Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (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, ... -
TENET: a new hybrid network architecture for adversarial defense
Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Springer Science and Business Media Deutschland GmbH, 2023-08)Deep neural network (DNN) models are widely renowned for their resistance to random perturbations. However, researchers have found out that these models are indeed extremely vulnerable to deliberately crafted and seemingly ... -
Uncertainty as a Swiss army knife: new adversarial attack and defense ideas based on epistemic uncertainty
Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Springer, 2022-04-02)Although state-of-the-art deep neural network models are known to be robust to random perturbations, it was verified that these architectures are indeed quite vulnerable to deliberately crafted perturbations, albeit being ... -
Unreasonable effectiveness of last hidden layer activations for adversarial robustness
Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Institute of Electrical and Electronics Engineers Inc., 2022)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 function on the logits to get the probability ... -
Using uncertainty metrics in adversarial machine learning as an attack and defense tool
Tuna, Ömer Faruk (Işık Ünivresitesi, 2022-12-19)Deep Neural Network (DNN) models are widely renowned for their resistance to random perturbations. However, researchers have found out that these models are indeed extremely vulnerable to deliberately crafted and seemingly ...