papers AI Learner
The Github is limit! Click to go to the new site.

TequilaGAN: How to easily identify GAN samples

2018-07-13
Rafael Valle, Wilson Cai, Anish Doshi

Abstract

In this paper we show strategies to easily identify fake samples generated with the Generative Adversarial Network framework. One strategy is based on the statistical analysis and comparison of raw pixel values and features extracted from them. The other strategy learns formal specifications from the real data and shows that fake samples violate the specifications of the real data. We show that fake samples produced with GANs have a universal signature that can be used to identify fake samples. We provide results on MNIST, CIFAR10, music and speech data.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1807.04919

PDF

https://arxiv.org/pdf/1807.04919


Similar Posts

Comments