A New Approach for Effective Malware Detection in Android-based Devices

A New Approach for Effective Malware Detection in Android-based Devices

Recently Android security has been considered by researchers since it is targeted by malware developers due to its wide usage for mobile phones, tablets, and other devices. Android security mainly relies on user decisions regarding to installing applications (apps) by approving their requested permissions. Therefore, systematic user assistance for making appropriate decisions can significantly improve the security of Android based devices. In this study, a new metric is introduced for effective risk computation of untrusted apps based on their required permissions. The proposed metric leverages both frequency of permission usage in malwares and rarity of them in normal apps. This metric can be directly used by the mobile owner to make better decisions or by Android markets to filter out suspicious apps for further analysis. Empirical evaluations show that the proposed metric has higher detection rates and is more effective than recently proposed risk score measurements.