A Framework for Assessing Factors Influencing User Interaction for Touch-based Biometrics

Touch-based behavioural biometrics is an emerging technique for passive and transparent user authentication on mobile devices. It utilises dynamics mined from users' touch actions to model behaviour. The interaction of the user with the mobile device using touch is an important aspect to investigate as the interaction errors can influence the stability of sample donation and overall performance of the implemented biometric authentication system. In this paper, we are outlining a data collection framework for touch-based behavioural biometric modalities (signature, swipe and keystroke dynamics) that will enable us to study the influence of environmental conditions and body movement on the touch-interaction. In order to achieve this, we have designed a multi-modal behavioural biometric data capturing application “Touchlogger” that logs touch actions exhibited by the user on the mobile device. The novelty of our framework lies in the collection of users' touch data under various usage scenarios and environmental conditions. We aim to collect touch data in two different environments - indoors and outdoors, along with different usage scenarios - whilst the user is seated at a desk, walking on a treadmill, walking outdoors and seated on a bus. The range of collected data may include swiping, signatures using finger and stylus, alphabetic, numeric keystroke data and writing patterns using a stylus.