Header menu link for other important links
X
DNDNet: Reconfiguring CNN for adversarial robustness
A. Goel, A. Agarwal, , , N.K. Ratha
Published in IEEE Computer Society
2020
Volume: 2020-June
   
Pages: 103 - 110
Abstract
Several successful adversarial attacks have demonstrated the vulnerabilities of deep learning algorithms. These attacks are detrimental in building deep learning based dependable AI applications. Therefore, it is imperative to build a defense mechanism to protect the integrity of deep learning models. In this paper, we present a novel "defense layer" in a network which aims to block the generation of adversarial noise and prevents an adversarial attack in black-box and gray-box settings. The parameter-free defense layer, when applied to any convolutional network, helps in achieving protection against attacks such as FGSM, L2, Elastic-Net, and DeepFool. Experiments are performed with different CNN architectures, including VGG, ResNet, and DenseNet, on three databases, namely, MNIST, CIFAR-10, and PaSC. The results showcase the efficacy of the proposed defense layer without adding any computational overhead. For example, on the CIFAR-10 database, while the attack can reduce the accuracy of the ResNet-50 model to as low as 6.3%, the proposed "defense layer" retains the original accuracy of 81.32%. © 2020 IEEE.
About the journal
JournalData powered by TypesetIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
PublisherData powered by TypesetIEEE Computer Society
ISSN21607508