The use of Convolutional Neural Network for Malware Classification

Abstract

Digital security is confronting an immense risk from malware or malicious software. In recent years, there has been an increase in the volume of malware, reaching above 980 million in 2019*. To identify and classify this pernicious software, complex details and patterns among them are to be gathered, segregated, and analyzed. In this regard, Convolutional Neural Networks (CNN) – an architecture of Deep Neural Networks (DDN) can offer a more efficient and accurate solution than Conventional Neural Network (NN) systems.In this paper, we have looked into the consequences of using conventional NN systems and the benefits of using CNN on a sample of malware provided by Microsoft. In 2015, Microsoft announced a malware classification challenge and released more than 21,000 malware samples. Many interesting solutions were put forward by scientists and students around the world. Inspired by their efforts we also have put forward a method. We have converted the malware binary files into images and then trained a CNN model for identification and categorization of this malware to their respective families. From this method, we achieved a high percentage accuracy of 98.88%.