Adaptive Phone Orientation Method for Continuous Authentication Based on Mobile Motion Sensors

Abstract

With the popularity of mobile terminals and the convenience of mobile operating, more and more private data is stored in mobile phones, which makes users pay more attention to mobile security. The data of mobile motion sensors are used to construct the user's behavioral characteristics and biometric characteristics. The principle is to capture the subtle changes in the smartphones caused by the user holding smartphones and touching screens. These changes are unique to different users. This paper studies the effects of mobile phone orientations on continuous authentication based on mobile motion sensors. Additionally, this paper constructs an adaptive phone orientation method for continuous authentication. An orientation detection model is constructed using K-means and Random Forest. The authentication model is constructed by using one-class SVM. Meanwhile, our experiments show that the data of mobile motion sensors are great difference in different phone orientations. We believe considering the situation of multi-orientations data affecting authentication accuracy. The adaptive phone orientation method can better fit for the scenarios where users use mobile devices in different phone orientations. Considering the orientation of the data will improve the robustness of the system and the accuracy of authentication.