Generative adversarial network (GAN) is the most exciting machine leing breakthrough in recent years, and it trains the leing model by finding the Nash equilibrium of a two-player zero-sum game. GAN is composed of a generator and a discriminator, both trained with the adversarial leing mechanism. In this paper, we introduce and investigate the use of GAN for novelty detection. In training, GAN les from ordinary data. Then, using previously unknown data, the generator and the discriminator with the designed decision boundaries can both be used to separate novel patts from ordinary patts. The proposed GAN-based novelty detection method demonstrates a competitive performance on the MNIST digit database and the Tennessee Eastman (TE) benchmark process compared with the PCA-based novelty detection methods using Hotelling’s T 2 and squared prediction error statistics.