We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Chained Dual-Generative Adversarial Network: A Generalized Defense Against Adversarial Attacks.
- Authors
Singh, Amitoj Bir; Awasthi, Lalit Kumar; Urvashi; Shorfuzzaman, Mohammad; Alsufyani, Abdulmajeed; Uddin, Mueen
- Abstract
Neural networks play a significant role in the field of image classification. When an input image is modified by adversarial attacks, the changes are imperceptible to the human eye, but it still leads to misclassification of the images. Researchers have demonstrated these attacks to make production self-driving cars misclassify StopRoad signs as 45 Miles Per Hour (MPH) road signs and a turtle being misclassified as AK47. Three primary types of defense approaches exist which can safeguard against such attacks i.e., Gradient Masking, Robust Optimization, and Adversarial Example Detection. Very few approaches use Generative Adversarial Networks (GAN) for Defense against Adversarial Attacks. In this paper, we create a new approach to defend against adversarial attacks, dubbed Chained Dual-Generative Adversarial Network (CD-GAN) that tackles the defense against adversarial attacks by minimizing the perturbations of the adversarial image using iterative oversampling and undersampling using GANs. CD-GAN is created using two GANs, i.e., CDGAN's Sub-ResolutionGANandCDGAN's Super-ResolutionGAN. The first is CDGAN's Sub-Resolution GAN which takes the original resolution input image and oversamples it to generate a lower resolution neutralized image. The second is CDGAN's Super-Resolution GAN which takes the output of the CDGAN's Sub-Resolution and undersamples, it to generate the higher resolution image which removes any remaining perturbations. Chained Dual GAN is formed by chaining these two GANs together. Both of these GANs are trained independently. CDGAN's Sub-Resolution GAN is trained using higher resolution adversarial images as inputs and lower resolution neutralized images as output image examples. Hence, this GAN downscales the image while removing adversarial attack noise. CDGAN's Super-Resolution GAN is trained using lower resolution adversarial images as inputs and higher resolution neutralized images as output images. Because of this, it acts as an Upscaling GAN while removing the adversarial attak noise. Furthermore, CD-GAN has a modular design such that it can be prefixed to any existing classifier without any retraining or extra effort, and can defend any classifier model against adversarial attack. In this way, it is a Generalized Defense against adversarial attacks, capable of defending any classifier model against any attacks. This enables the user to directly integrate CD-GANwith an existing production deployed classifier smoothly.CD-GAN iteratively removes the adversarial noise using a multi-step approach in a modular approach. It performs comparably to the state of the arts with mean accuracy of 33.67 while using minimal compute resources in training.
- Subjects
HIGH resolution imaging; GENERATIVE adversarial networks; MASTS &; rigging; TRAFFIC signs &; signals; ROBUST optimization; MODULAR design; DRIVERLESS cars
- Publication
Computers, Materials & Continua, 2023, Vol 74, Issue 2, p2541
- ISSN
1546-2218
- Publication type
Article
- DOI
10.32604/cmc.2023.032795