Towards Automated Software Testing with Generative Adversarial Networks

Abstract

This paper discusses software testing methods based on Generative Adversarial Network (GAN). GAN is a generative model that can create new data instances that resemble training data. A GAN consists of a generator network and a discriminator network. In our testing scheme, the trained generator network is used as a test case generator. In addition, we propose a framework with GAN, which is a testing strategy used to increase the test coverage.