Leveraging machine learning for biometric authentication is an area of research that has seen a lot of progress within the past decade. Keystroke authentication based on machine and deep learning binary classifiers aims to develop a robust model to distinguish a user from an adversary based on typing metrics (keystrokes). While keystroke authentication started with fixed text, where users types the same data, the shift has been to free text data where every user’s data varies. However, popular deep learning classifiers are bottlenecked by the large amount of data needed to make them efficient. This work solves the data bottleneck issue in keystroke authentication’s binary classification problem by utilizing Generative Adversarial Networks to generate free text keystroke data with a valid label. Furthermore, the produced synthetic data are used to train a Convolutional Neural Network, attempting to push the Equal Error Rate rate even lower and at the same time resolve the data bottleneck.