While deep neural networks have proven to be a powerful tool for many recognition and classification tasks, their stability properties are still not well understood. In the past, image classifiers have been shown to be vulnerable to so-called adversarial attacks, which are created by additively perturbing the correctly classified image. In this paper, we propose the ADef algorithm to construct a different kind of adversarial attack created by iteratively applying small deformations to the image, found through a gradient descent step. We demonstrate our results on MNIST with convolutional neural networks and on ImageNet with Inception-v3 and ResNet-101.
@article{arxiv.1804.07729,
title = {ADef: an Iterative Algorithm to Construct Adversarial Deformations},
author = {Rima Alaifari and Giovanni S. Alberti and Tandri Gauksson},
journal= {arXiv preprint arXiv:1804.07729},
year = {2019}
}