Touch-input based continuous authentication using gesture-level and session-level features

Nowadays, touchscreen mobile devices make up a larger share in the market. Users often use these devices to store personal and sensitive data. This necessitate to find more effective and robust methods to continuously authenticate touch-based mobile device users. In this paper, we propose two levels of behavioral touch features that can be extracted from raw touchscreen logs and demonstrate that different users populate distinct subspaces of this feature space. In an experiment designed to test how this behavioral pattern exhibits consistency over time, we collected touch data from users interacting with a touch-based tablet device using the most common gestures, i.e., scrolling in all directions; up, down, right and left, tapping, zoom-in and out etc. We propose a classification framework that learns the touch behavior of a user during an enrollment phase and is able afterwards to authenticate users by monitoring their behavior in performing input touch actions. We build two models of features from two different perspectives to study which model will give us the higher accuracy in classification; the low level features model obtained through the stoke level data or the high level abstracted features model obtained through the session level data. Our results indicate the possibility of the continuous authentication for touch-input users with higher promises for session level features than gesture level features.