Mangla, Puneet and Balasubramanian, Vineeth N and Varshney, Sakshi and et al, .
(2019)
AdvGAN++ : Harnessing latent layers for adversary generation.
arXiv.org.
Abstract
Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance. Recently proposed AdvGAN, a GAN based approach, takes input image as a prior for generating adversaries to target a model. In this work, we show how latent features can serve as better priors than input images for adversary generation by proposing AdvGAN++, a version of AdvGAN that achieves higher attack rates than AdvGAN and at the same time generates perceptually realistic images on MNIST and CIFAR10 datasets.
Actions (login required)
 |
View Item |
Altmetric
Altmetric