Implementing multiple biometric features for a recall-based graphical keystroke dynamics authentication system on a smart phone

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 With the growing use of smart phones, the traditional keypad on mobile phones has been replaced by touch screen devices.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%).