Research Article
Measuring How We Play: Authenticating Users with Touchscreen Gameplay
@INPROCEEDINGS{10.1007/978-3-319-90740-6_9, author={Jonathan Voris}, title={Measuring How We Play: Authenticating Users with Touchscreen Gameplay}, proceedings={Mobile Computing, Applications, and Services. 9th International Conference, MobiCASE 2018, Osaka, Japan, February 28 -- March 2, 2018, Proceedings}, proceedings_a={MOBICASE}, year={2018}, month={5}, keywords={Active authentication Behavioral biometrics Games for security Gamification Machine learning Mobile authentication SVM Useful games}, doi={10.1007/978-3-319-90740-6_9} }- Jonathan Voris
Year: 2018
Measuring How We Play: Authenticating Users with Touchscreen Gameplay
MOBICASE
Springer
DOI: 10.1007/978-3-319-90740-6_9
Abstract
Mobile devices are being used to access and store an ever-increasing amount of sensitive data. Due to their compact form factor, mobile devices can be easily lost or stolen. Yet users frequently choose not to enable authentication or select authentication methods which are insufficient to protect their devices, placing user information at risk. In this paper, we propose the use of a behavioral biometric based approach to authentication that functions by modeling the manner in which users interact wit mobile games, which are one of the most popular uses of mobile devices. We conducted an IRB approved study in which 30 participants were asked to play three popular Android games as well as utilize a mobile touchscreen without any gameplay prompting. We extracted features from users’ touchscreen activity during these interactions, then applied a Support Vector Machine to classify users based on patterns which emerged from their usage during the game. Our results indicate that using gameplay as a behavioral biometric is an effective means of authenticating users to their mobile devices, but care must be taken to select a game which encourages users to make frequent distinctive gestures.
