English

AdvGAN++ : Harnessing latent layers for adversary generation

Computer Vision and Pattern Recognition 2019-12-25 v2 Machine Learning

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 CIFAR-10 datasets.

Keywords

Cite

@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}
}

Comments

Accepted at Neural Architects Workshop, ICCV 2019

R2 v1 2026-06-23T10:37:55.921Z