TENET: a new hybrid network architecture for adversarial defense
Yükleniyor...
Tarih
2023-08
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Springer Science and Business Media Deutschland GmbH
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
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 imperceptible perturbations of the input, referred to as adversarial examples. Adversarial attacks have the potential to substantially compromise the security of DNN-powered systems and posing high risks especially in the areas where security is a top priority. Numerous studies have been conducted in recent years to defend against these attacks and to develop more robust architectures resistant to adversarial threats. In this study, we propose a new architecture and enhance a recently proposed technique by which we can restore adversarial samples back to their original class manifold. We leverage the use of several uncertainty metrics obtained from Monte Carlo dropout (MC Dropout) estimates of the model together with the model’s own loss function and combine them with the use of defensive distillation technique to defend against these attacks. We have experimentally evaluated and verified the efficacy of our approach on MNIST (Digit), MNIST (Fashion) and CIFAR10 datasets. In our experiments, we showed that our proposed method reduces the attack’s success rate lower than 5% without compromising clean accuracy.
Açıklama
This work was supported by The Scientific and Technological Research Council of Turkey (TUBITAK) through the 1515 Frontier Research and Development Laboratories Support Program under Project 5169902, and has been partly funded by the European Union’s Horizon Europe research and innovation programme and Smart Networks and Services Joint Undertaking (SNS JU) under Grant Agreement No: 101096034 (VERGE Project).
Anahtar Kelimeler
Adversarial machine learning, Model uncertainty, Monte Carlo dropout sampling, Robustness, Distillation, Monte Carlo methods, Network architecture, Uncertainty analysis, Hybrid network, Loss functions, Machine-learning, Modeling uncertainties, Neural network model, Random perturbations, Uncertainty, Deep neural networks
Kaynak
International Journal of Information Security
WoS Q Değeri
Q2
Scopus Q Değeri
Q1
Cilt
22
Sayı
4
Künye
Tuna, Ö. F., Çatak, F. Ö. & Eskil, M. T. (2023). TENET: a new hybrid network architecture for adversarial defense. International Journal of Information Security, 22(4), 987-1004. doi:10.1007/s10207-023-00675-1
