Malware detection in Android devices Using Machine Learning

Abstract

The number of devices that are using Android as their Operating System has increased steadily over the years. There is a growing number of types of devices that are making use of this Operating System that is being improved so frequently. The steady growth in number of devices using this Operating System has unfortunately beckoned unwavering attempts to attack these devices for various reasons. There is a great rise in the number of malicious software, commonly referred to as malware, that are aimed at compromising the functioning of these android devices. Consequently, this has spackled the need to develop techniques that aim at detecting these bad pieces of code in the devices. This paper presents a literature review of some commonly used machine learning algorithms in malware detection in android devices and proposes a model for malware detection with high accuracy with less false positives by combining Support Vector Machine and Random Forest in the detection process. The performance and accuracy of the model have will be polished up with the use of proper features, feature selection techniques and also feature reduction algorithms alongside enough dataset used for training and testing of the model.