In this chapter, you will learn how to implement TequilaGAN: How to easily identify GAN samples. You will learn how to understand what the underlying characteristics of Generative Adversarial Networks (GANs) data are and how to identify data to differentiate real data from fake data. You will implement strategies to easily identify fake samples generated with the GAN 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.
The following topics will be covered in this chapter:
- Identifying GAN samples
- Feature extraction
- Metrics
- Experiments
