5 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 5 / 5
Yayın Unreasonable effectiveness of last hidden layer activations for adversarial robustness(Institute of Electrical and Electronics Engineers Inc., 2022) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa TanerIn 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 scores of each class. In this type of architectures, the loss value of the classifier against any output class is directly proportional to the difference between the final probability score and the label value of the associated class. Standard White-box adversarial evasion attacks, whether targeted or untargeted, mainly try to exploit the gradient of the model loss function to craft adversarial samples and fool the model. In this study, we show both mathematically and experimentally that using some widely known activation functions in the output layer of the model with high temperature values has the effect of zeroing out the gradients for both targeted and untargeted attack cases, preventing attackers from exploiting the model's loss function to craft adversarial samples. We've experimentally verified the efficacy of our approach on MNIST (Digit), CIFAR10 datasets. Detailed experiments confirmed that our approach substantially improves robustness against gradient-based targeted and untargeted attack threats. And, we showed that the increased non-linearity at the output layer has some ad-ditional benefits against some other attack methods like Deepfool attack.Yayın Closeness and uncertainty aware adversarial examples detection in adversarial machine learning(Elsevier Ltd, 2022-07) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa TanerWhile 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 vulnerabilities make it challenging to deploy Deep Neural Network (DNN) models in security-critical areas. Recently, many research studies have been conducted to develop defense techniques enabling more robust models. In this paper, we target detecting adversarial samples by differentiating them from their clean equivalents. We investigate various metrics for detecting adversarial samples. We first leverage moment-based predictive uncertainty estimates of DNN classifiers derived through Monte-Carlo (MC) Dropout Sampling. We also introduce a new method that operates in the subspace of deep features obtained by the model. We verified the effectiveness of our approach on different datasets. Our experiments show that these approaches complement each other, and combined usage of all metrics yields 99 % ROC-AUC adversarial detection score for well-known attack algorithms.Yayın Uncertainty as a Swiss army knife: new adversarial attack and defense ideas based on epistemic uncertainty(Springer, 2022-04-02) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa TanerAlthough 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 quasi-imperceptible. These vulnerabilities make it challenging to deploy deep neural network models in the areas where security is a critical concern. In recent years, many research studies have been conducted to develop new attack methods and come up with new defense techniques that enable more robust and reliable models. In this study, we use the quantified epistemic uncertainty obtained from the model's final probability outputs, along with the model's own loss function, to generate more effective adversarial samples. And we propose a novel defense approach against attacks like Deepfool which result in adversarial samples located near the model's decision boundary. We have verified the effectiveness of our attack method on MNIST (Digit), MNIST (Fashion) and CIFAR-10 datasets. In our experiments, we showed that our proposed uncertainty-based reversal method achieved a worst case success rate of around 95% without compromising clean accuracy.Yayın Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples(Springer, 2022-03) Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa TanerDeep 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.Yayın BOUN-ISIK participation: an unsupervised approach for the named entity normalization and relation extraction of Bacteria Biotopes(Association for Computational Linguistics (ACL), 2019-11-04) Karadeniz, İlknur; Tuna, Ömer Faruk; Özgu, ArzucanThis 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 (BB-norm) and the identification of the relations between the entities given a biomedical text (BB-rel). For the normalization of entities, we utilized word embeddings and syntactic re-ranking. For the relation extraction task, pre-defined rules are used. Although both approaches are unsupervised, in the sense that they do not need any labeled data, they achieved promising results. Especially, for the BB-norm task, the results have shown that the proposed method performs as good as deep learning based methods, which require labeled data.
