AdvGAN++: Harnessing Latent Layers for Adversary Generation

Surgan Jandial, Puneet Mangla, Sakshi Varshney, Vineeth Balasubramanian
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
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
more » ... me generates perceptually realistic images on MNIST and CIFAR-10 datasets.
doi:10.1109/iccvw.2019.00257 dblp:conf/iccvw/JandialMVB19 fatcat:c4advuefhbbtzp5t4jfeieaouy