RPNDroid: Android Malware Detection using Ranked Permissions and Network Traffic
Madan Upadhayay, Ashutosh Sharma, Gourav Garg, Anshul Arora
Abstract
The number of malware attacks on the Android platform has escalated over the past few years. 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 hybrid Android malware detector based on ranked permissions and network traffic features. 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 merge the ranked permissions with the network traffic features to form a hybrid vector for all the apps in the dataset. Finally, we propose a novel algorithm that applies machine learning algorithms on the hybrid vectors consisting of permissions and traffic features to detect Android malware. The experimental results demonstrate that by using the hybrid approach, we could achieve 95.96% detection accuracy with the proposed algorithm.