Poster
ADef: an Iterative Algorithm to Construct Adversarial Deformations
Rima Alaifari · Giovanni S Alberti · Tandri Gauksson
Great Hall BC #26
Keywords: [ deep neural networks ] [ adversarial examples ] [ computer vision ] [ deformations ]
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.
Live content is unavailable. Log in and register to view live content