Touch-dynamics based Behavioural Biometrics on Mobile Devices – A Review from a Usability and Performance Perspective
Elakkiya Ellavarason, Richard Guest, Farzin Deravi, Raul Sanchez-Riello, Barbara Corsetti
Abstract
Over the past few years, there has been an exponential increase in the percentage of people owning and using a smart phone. These devices have sensor-rich touchscreens that can capture sensitive biometric features such as keystroke typing and finger-swiping patterns. Touch-dynamics based behavioural biometrics is a time-based assessment of how a user performs a particular touch task on a mobile device. Several performance-focused surveys already exist. In this article, building upon the existing reviews, we have examined studies on touch-dynamics based behavioural biometrics based on usability and its impact on authentication performance. We also emphasize the need for shifting the focus on usability during performance evaluations by presenting a consolidated list of usability and ergonomic-based factors that influence user interaction and cause performance variations. In this article, we report and review the usability evaluations: user acceptance studies and performance-based studies influencing the user interaction process on three specific touch-dynamics based modalities—signature, keystroke, and swipe. With regards to performance, we present a comparative analysis of error rates and accuracy of various research works undertaken. Additionally, we present a consolidated list of public datasets and discuss evolving vulnerabilities of touch-dynamics based behavioural biometrics, their adopted attack models, and their feasibility. Finally, we present our assessment of this domain's existing unresolved problems that could pave the way for future research.