DeepFool: A simple and accurate method to fool deep neural networks

State-of-the-art deep neural networks have achieved impressive results on many image classification tasks. However, these same architectures have been shown to be unstable to small, well sought, perturbations of the images. In this paper, we fill this gap and propose the DeepFool framework to efficiently compute perturbations that fools deep network and thus reliably quantify the robustness of arbitrary classifiers.

via http://gitxiv.com/posts/iZpWrvKdXmtRaQusa/deepfool-a-simple-and-accurate-method-to-fool-deep-neural