Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples
Citation
Tuna, Ö. F., Çatak, F. Ö. & Eskil, M. T. (2022). Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples. Multimedia Tools and Applications, 81(8) 11479-11500. doi:10.1007/s11042-022-12132-7Abstract
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, termed as adversarial samples. In recent years, numerous studies have been conducted in this new area called ``Adversarial Machine Learning” to devise new adversarial attacks and to defend against these attacks with more robust DNN architectures. However, most of the current research has concentrated on utilising model loss function to craft adversarial examples or to create robust models. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes by which we perturb the input to the shifted-domain regions where the model has not been trained on. We proposed new attack ideas by exploiting the difficulty of the target model to discriminate between samples drawn from original and shifted versions of the training data distribution by utilizing epistemic uncertainty of the model. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.14%, 82.96% to 90.13% and 89.44% to 91.06% on MNIST Digit, MNIST Fashion and CIFAR-10 datasets, respectively.
Source
Multimedia Tools and ApplicationsVolume
81Issue
8The following license files are associated with this item:
Related items
Showing items related by title, author, creator and subject.
-
Extension of conventional co-training learning strategies to three-view and committee-based learning strategies for effective automatic sentence segmentation
Dalva, Doğan; Güz, Ümit; Gürkan, Hakan (IEEE, 2018)The objective of this work is to develop effective multi-view semi-supervised machine learning strategies for sentence boundary classification problem when only small sets of sentence boundary labeled data are available. ... -
Effective semi-supervised learning strategies for automatic sentence segmentation
Dalva, Doğan; Güz, Ümit; Gürkan, Hakan (Elsevier Science BV, 2018-04-01)The primary objective of sentence segmentation process is to determine the sentence boundaries of a stream of words output by the automatic speech recognizers. Statistical methods developed for sentence segmentation requires ... -
Aynı oteli temsil eden farklı kayıtlar için akıllı eşleştirme
Bayrak, Ahmet Tuğrul; Özbek, Eyüp Erkan; Kestepe, Sedat; Yıldız, Olcay Taner (Institute of Electrical and Electronics Engineers Inc., 2019-09)Otel sayısının her geçen gün arttığı turizm sektöründe, aracı firmaların tüm oteller ile ayrı ayrı çalışma imkanı bulunmadığından, firmalar dünya üzerinde bir çok otelle anlaşması bulunan servis sağlayıcılarıyla beraber ...