Efficient Characterization and Classification of Malware Using Deep Learning

Abstract

Bad actors have embraced automation to construct malware, and current analysis systems cannot keep up with the ever-increasing load of malware being created daily. Additionally, some static analysis of malware can be computationally expensive, and not all static analysis should be considered for every sample that is part of a large malware dataset. As a result, highly expressive and inexpensive characterizations of malicious code, coupled with low resource machine learning classification platforms are required. In this paper, we use deep learning to build a meta-model that finds the simplest classifiers to characterize and assign malware into their corresponding families. Using static analysis of malware, we generate descriptive features to be used in conjunction with deep learning, in order to predict malware families. Our meta-model can determine when simple and less expensive malware characterization will suffice to accurately classify malicious executables, or when more computationally expensive descriptions are required. Finally, our meta-model is able to predict the simplest features and models to classify malware with an accuracy of up to 90%.