AdvGAN++: Harnessing Latent Layers for Adversary Generation

Surgan Jandial, Puneet Mangla, Sakshi Varshney, Vineeth Balasubramanian

ICCVW 2019 pp. 2045-2048

doi:10.1109/ICCVW.2019.00257 /iccvw/2019/jandial2019iccvw-advgan/

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.

PDF ICCVW Semantic Scholar

Cite

Text

Jandial et al. "AdvGAN++: Harnessing Latent Layers for Adversary Generation." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00257

Markdown

[Jandial et al. "AdvGAN++: Harnessing Latent Layers for Adversary Generation." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/jandial2019iccvw-advgan/) doi:10.1109/ICCVW.2019.00257

BibTeX

@inproceedings{jandial2019iccvw-advgan,
  title     = {{AdvGAN++: Harnessing Latent Layers for Adversary Generation}},
  author    = {Jandial, Surgan and Mangla, Puneet and Varshney, Sakshi and Balasubramanian, Vineeth},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {2045-2048},
  doi       = {10.1109/ICCVW.2019.00257},
  url       = {https://mlanthology.org/iccvw/2019/jandial2019iccvw-advgan/}
}