Recently, cyber-attacks to smart energy grid has become a critical subject for Energy System Operators (ESOs). To keep the energy grid cyber-secured, the attacker’s behavior, resources and goals must be modeled properly. Then, the counter-measurement actions can be designed based on the attacker's model. In this paper, a new zero-sum game based on the Generative Adversarial Networks (GANs) is presented. The attacker to energy smart grid pursues two objects. The first goal is to be undetected by the system defender, and the second goal is to make profit via its False Data Injection (FDI) into the system. On the defender hand, the ESO needs to detect FDI using fast and reliable models. Thus, each party tries to defeat the other part. GANs are deep layer networks which consist of two rivals networks: the generator and the discriminator. The Generator Network (GN) aims to create the data similar to real data (plays the attacker role) and the Discriminator Network (DN) wants to properly detect whether the data is real or faked by the GN (plays the system defender role). In this paper, a new algorithm is presented to model both the attacker and ESO in the GAN frame work. Finally, A five-bus smart grid case is considered to show the effectiveness of the presented algorithm.