AdvGAN++: Harnessing Latent Layers for Adversary Generation

Surgan Jandial, Puneet Mangla, Sakshi Varshney, Vineeth Balasubramanian; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Jandial_2019_ICCV,
author = {Jandial, Surgan and Mangla, Puneet and Varshney, Sakshi and Balasubramanian, Vineeth},
title = {AdvGAN++: Harnessing Latent Layers for Adversary Generation},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
month = {Oct},
year = {2019}
}