Adversarial examples are a hot topic due to their abilities to fool a classifiers prediction. There are two strategies to create such examples, one uses the attacked classifiers gradients, while the other only requires access to the clas-sifiers prediction. This is particularly appealing when the classifier is not full known (black box model). In this paper, we present a new method which is able to generate natural adversarial examples from the true data following the second paradigm. Based on Generative Adversarial Networks (GANs) [5], it reweights the true data empirical distribution to encourage the classifier to generate ad-versarial examples. We provide a proof of concept of our method by generating adversarial hyperspectral signatures on a remote sensing dataset.
تحميل البحث