Android X-Ray - A system for Malware Detection in Android apps using Dynamic Analysis

Abstract

In recent years, mobile malware takes anywhere between several hours to several days to screen an app for malicious activity. More than 6000 apps are added to the Google Play Store everyday on average. Security analysts face an uphill battle against malware developers as the complexity of malware and code obfuscation techniques are constantly increasing. Currently, most research focuses on the development and application of machine learning techniques for malware detection. However, their success has been limited due to a lack of depth in the data sets available for training models. This paper uses a new method of Dynamic Analysis for Android apps to extract large amounts of information on the behavior of any app which can then be used for training models or to enable security analysts to take an informed decision quickly.