Mobile devices are becoming increasingly popular. The widespread use exposes individuals to unintentionally sharing sensitive information that could allow direct access to the mobile device. This paper implements and tests a user verification system based on touch dynamics biometrics while typing a Personal Identification Number (PIN). The proposed framework includes several features and feature selection. The classification problem has been considered in terms of one-class and binary classifiers. The proposed approach can outperform the current State of the art on the binary classification problem on the considered dataset, achieving an Equal Error Rate (EER) of 0.01%.