TequilaGAN: How to easily identify GAN samples
arXiv:1807.04919
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.
arXiv comment10 pages, 16 figures
References in corpus (7)
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Improved Training of Wasserstein GANs
- Improved Techniques for Training GANs
- Energy-based Generative Adversarial Network
- A Note on the Inception Score
- Least Squares Generative Adversarial Networks
- Attacking Speaker Recognition With Deep Generative Models
Cited by in corpus (5)
- Leveraging Frequency Analysis for Deep Fake Image Recognition
- Detecting GAN generated Fake Images using Co-occurrence Matrices
- Forbidden knowledge in machine learning -- Reflections on the limits of research and publication
- Detection, Attribution and Localization of GAN Generated Images
- One-Shot GAN Generated Fake Face Detection