Implementing multiple biometric features for a recall-based graphical keystroke dynamics authentication system on a smart phone. (July 2015)

• Record Type: Journal Article
• Authors: Liu, Chao-Liang; Tsai, Cheng-Jung; Chang, Ting-Yi; Tsai, Wang-Jui; Zhong, Po-Kai
• Is Part Of: Journal of network and computer applications. Volume 53(2015)
• Page Start: 128
• Page End: 139
• Publication Date: 2015-07
• Subjects: Authentication -- Biometric -- Keystroke dynamics -- Touch screen -- Graphical password -- Android pattern lock; Microcomputers -- Periodicals; Computer networks -- Periodicals; Application software -- Periodicals; Micro-ordinateurs -- Périodiques; Réseaux d'ordinateurs -- Périodiques; Logiciels d'application -- Périodiques; Application software; Computer networks; Microcomputers; Periodicals; 004.05; 004
• DOI: 10.1016/j.jnca.2015.03.006
• Languages: English
• ISSNs: 1084-8045

Abstract

Abstract: Keystroke Dynamics-based Authentication (KDA) is a type of behavioral biometric method. It verifies user identity via the keystroke features gathered from the keystroke events provided by users on a QWERTY keyboard. With the growing use of smart phones, the traditional keypad on mobile phones has been replaced by touch screen devices. The keypad-based KDA is no longer suitable for smart phones. This paper proposes a KDA system implemented using multiple biometric features applied to the pattern lock layout on a smart phone. Except for the time, pressure and size of the keystroke features presented in previous research, we additionally adopted a novel angle keystroke feature and determined the best combination of these features in a series of experiments. As the results show, with 10 training samples involved, the combination of time, pressure and angle offers the best utility (Equal Error Rate of 3.03%).