Screen Unlocking by Spontaneous Flick Reactions with One-Class Classification Approaches

Physical biometrics technologies are introduced to the login process on smart devices. However, many of them have several disadvantages: requirement of embedding special sensor, limited environment to use and copy of key information for authentication. In this research, we proposed a new biometrics technique which can capture user's inimitable behavioral features in his/her spontaneous flick reactions on a touch-screen display for unlocking the device when it wakes up. For practical use of the technique, we adopted one-class classification approaches and they achieved about 1-2% EERs for 2500 samples from 50 subjects.

I. Introduction

Smart devices such as smartphone, tablet and wearable devices have been recently getting used all over the world. With the spread of these devices, information security on them has been highly demanded. Then, PIN (Personal Identification Number), password, and pattern have been introduced to unlock the screen when the smart device system starts up, but users are required to remember the strings or patterns to unlock the systems. Furthermore, it is vulnerable to brute-force attacks, and user's finger smudges on a touchscreen display can be traced by attackers. On the other hand, it is widely known that biometrics technology enables users to memorize no information for unlocking the system, and biometrics information is difficult to be copied by attackers because the technology authenticates users by capturing their physical or/and behavioral features [1], [2]. At present, several types of physical biometrics are being introduced to smart devices [3], [4]. However, special sensors causing additional product costs such as a fingerprint reader are required in most of practical physical biometrics for mobile devices, and environmental conditions for them such as the reader's dirtiness and ambient brightness could negatively affect their authentication performance. Furthermore, in the case of biometrics technology with user's physical features such as fingerprint and face, the features could be stolen by special gel or a camera, and then they cannot be replaced because of non-cancelable, fixed physical features.