RPDroid: Android Malware Detection using Ranked Permissions presented at CNSA 2020

by Madan Upadhayay, Ashutosh Sharma, Gourav Arora,

Summary : The number of malware attacks on Android platform has escalated over the past few years. They pose significant threats such as financial loss, information leakage, and system damage. The seriousness of these attacks can be depicted from the fact that around 25 million Android smartphones were infected with malware within the first half of 2019. Keeping these threats in mind, we aim to develop a static permissions based Android malware detector. In this work, first, we find the permissions that are frequently present in normal and malicious apps and rank the permissions based upon their frequency in normal and malware dataset. Additionally, we applied different support thresholds to remove the unnecessary and redundant permissions from the rankings. Further, we propose a novel algorithm that uses the ranked permissions (that are above the specified threshold) and the machine learning algorithms to detect Android malware. The experimental results demonstrate that by using the Random Forest classifier and 5% support threshold, we could achieve 91.96% detection accuracy with the proposed algorithm on the minimum set of 19 permissions.