Android Malware Variant Detection by Comparing Traditional Antivirus

Abstract

Android is gradually becoming malware targeting it. According to the recent Symantec threat reports, the number of newly discovered mobile malware variants grew by 54% from 2016 to 2017. Malware writers used obfuscation techniques to create malware variants to evade detection by some tools detections or antivirus companies. it is difficult for antivirus to detect the signature of these variants if the database does not update. It is, therefore, essential to explore new ways to prevent, detect and counter cyberattacks. In these detection mechanisms, machine learning uses to create classifiers that determine whether an application is dangerous or not. In the research, we focus on Android malware detection in Android APK. We analyze obfuscation techniques used by malware writers to create malware variants. We analyze permission and API Calls from Android APK. We compare techniques and how it is not easy for traditional antivirus to detect malware variants.