Linux Kernel-based Feature Selection for Android Malware Detection

As usage of mobile increased, target of attackers has changed from PC to Mobile environment. In particular, various attacks have occurred in android platform because it has feature of open platform. To solve this problem, researches of machine learning-based malware detection continually have progressed. However, as version of Android platform continuously is updated, some feature that used in existing research could not collect any more. Therefore, we propose Linux kernel-based novel feature in order to detect malware in higher than android version 4.0. In addition, we perform feature selection to select optimal feature about foregoing feature. This way is able to improve performance of malware detection system. In experiment, by performing android malware detection through support vector machine classifier which has showed relatively good performance in existing studies, we show novel feature feasibility and validity.