Evaluation of Motion-Based Touch-Typing Biometrics for Online Banking

This paper presents a bimodal scheme - the mechanism which exploits the way the user enters her 8-digit PIN/password and the phone-movements while doing so, for user authentication in mobile banking/financial applications (apps). The scheme authenticates the user based on the timing differences of the entered strokes. Additionally, it provides an enhanced security by adding an unobservable layer based on the phone-movements. The scheme is assumed to be highly secure as mimicking the invisible touch-timings and the phone-movements could be extremely difficult. Our analysis is based on 2850 samples collected from 95 users through a 3-day unsupervised field experiment and using 3 multi-class classifiers. Random Forest (RF) classifier out-performed other two classifiers and provided a True Acceptance Rate (TAR) of 96%.