Generative Adversarial Perturbations

12/06/2017 ∙ by Omid Poursaeed, et al. ∙ 0

In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce image-agnostic and image-dependent perturbations for both targeted and non-targeted attacks. We also demonstrate that similar architectures can achieve impressive results in fooling classification and semantic segmentation models, obviating the need for hand-crafting attack methods for each task. Using extensive experiments on challenging high-resolution datasets such as ImageNet and Cityscapes, we show that our perturbations achieve high fooling rates with small perturbation norms. Moreover, our attacks are considerably faster than current iterative methods at inference time.



There are no comments yet.


page 9

page 10

page 11

page 12

page 13

page 14

page 15

page 21

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.