Leveraging GANs to combat adversarial examples

In 2014, Szegedy et al. published an ICLR paper with a surprising discovery: modern deep neural networks trained for image classification exhibit the following vulnerability: by making only slight alterations to an input image, it's possible to drastically fool a model that would otherwise classify the image correctly (say, as a dog), into outputting a completely wrong label (say, as a banana). Moreover, this attack is possible even with perturbations that are so tiny that a human couldn't distinguish the altered image from the original. These doctored images are called adversarial examples and the study of how to make neural networks robust to these attacks is an increasingly active area of machine learning research. This adversarial noise can be made robust. Labsix, a group of MIT students, showed that one can create adversarial examples in the physical world by 3d-printing a physical object, now affectionately called the adversarial turtle, that is classified as a rifle by state-of-the-art deep nets.