Network alignment (NA) consists on finding the optimal node correspondence between distinct networks (graphs). Previous works in this field have had various degrees of success. However, they rely on some strong assumptions of topological and/or attribute consistency among the aligned networks. Simultaneously, Generative Adversarial Networks (GANs), generative models that have achieved remarkable results on continuous data such as images and audio, have recently been successfully applied to tasks with discrete domains, such as text generation. This work presents our efforts into designing a GAN-based NA model to address the limitations of other approaches by exploiting (1) random walks' trait of being able to capture the local and global topological structure of networks and (2) GAN's ability to estimate the unknown distribution of the training data.