A SVM-Based Malware Detection Mechanism for Android Devices

Abstract

Currently, Android phones accounted for over 85 % of all smartphone sales as of 2017. Because the system allows users to install the unofficial apps, it will be targeted by malware easily. Using general anti-virus software to scan apps usually detected a known virus species only. As for new type of unknown variant, is not detectable normally. In this paper, we present a SVM-based mechanism to detect the malware and normal apps. The proposed idea scanning and recording features for both required and used permissions of the list. We adopt the LibSVM to classify the unknown apps. The experimental results indicate the accurate rate of 99% for the correct identification of both benign and malware even for the unknown applications. We propose not only a simple but also feasible approach to detect mobile apps.