End-to-end User Recognition using Touchscreen Biometrics
This work addresses user authentication for mobile device security, presenting an incremental improvement over existing methods.
The authors tackled user identification on mobile devices by using raw touchscreen data as behavioral biometrics, achieving a best result of 0.65% Equal Error Rate (EER) with their end-to-end deep neural network system.
We study the touchscreen data as behavioural biometrics. The goal was to create an end-to-end system that can transparently identify users using raw data from mobile devices. The touchscreen biometrics was researched only few times in series of works with disparity in used methodology and databases. In the proposed system data from the touchscreen goes directly, without any processing, to the input of a deep neural network, which is able to decide on the identity of the user. No hand-crafted features are used. The implemented classification algorithm tries to find patterns by its own from raw data. The achieved results show that the proposed deep model is sufficient enough for the given identification task. The performed tests indicate high accuracy of user identification and better EER results compared to state of the art systems. The best result achieved by our system is 0.65% EER.