Permission-Based Android Malware Detection

Abstract - Mobile devices have become popular in our lives since they offer almost the same functionality as personal computers. Among them Android-based mobile devices had appeared lately and they were now an ideal target for attackers. Android-based smartphone users can get free applications from Android Application Market. But these applications were not certified by legitimate organizations and they may contain malware applications that can steal privacy information for users. In this paper a framework that can detect android malware applications is proposed to help organizing Android Market. The proposed framework intends to develop a machine learning-based malware detection system on Android to detect malware applications and to enhance security and privacy of smartphone users. This system monitors various permissionbased features and events obtained from the android applications and analyses these features by using machine learning classifiers to classify whether the application is goodware or malware.