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 CIFAR-10 datasets.
@article{arxiv.1908.00706,
title = {AdvGAN++ : Harnessing latent layers for adversary generation},
author = {Puneet Mangla and Surgan Jandial and Sakshi Varshney and Vineeth N Balasubramanian},
journal= {arXiv preprint arXiv:1908.00706},
year = {2019}
}