TequilaGAN: How to easily identify GAN samples
This addresses the issue of detecting synthetic media for security and verification purposes, but it is incremental as it builds on existing GAN analysis methods.
The paper tackles the problem of identifying fake samples generated by GANs by proposing strategies based on statistical analysis and formal specifications, showing that GAN samples have a universal signature and providing results across multiple datasets like MNIST, CIFAR10, music, and speech.
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.