Machine Learning Aided Static Malware Analysis: A Survey and Tutorial

TL;DR

This paper provides a comprehensive survey and tutorial on machine learning techniques for static malware analysis, focusing on classifying Windows PE files and evaluating their effectiveness and generalization.

Contribution

It fills a research gap by systematically reviewing ML methods for static malware classification and offering practical guidance on their application and evaluation.

Findings

ML methods achieve high accuracy in static malware classification

The study demonstrates the generalization capability of different ML techniques

Experimental results highlight the trade-off between accuracy and complexity

Abstract

Malware analysis and detection techniques have been evolving during the last decade as a reflection to development of different malware techniques to evade network-based and host-based security protections. The fast growth in variety and number of malware species made it very difficult for forensics investigators to provide an on time response. Therefore, Machine Learning (ML) aided malware analysis became a necessity to automate different aspects of static and dynamic malware investigation. We believe that machine learning aided static analysis can be used as a methodological approach in technical Cyber Threats Intelligence (CTI) rather than resource-consuming dynamic malware analysis that has been thoroughly studied before. In this paper, we address this research gap by conducting an in-depth survey of different machine learning methods for classification of static characteristics of 32-bit malicious Portable Executable (PE32) Windows files and develop taxonomy for better understanding of these techniques. Afterwards, we offer a tutorial on how different machine learning techniques can be utilized in extraction and analysis of a variety of static characteristic of PE binaries and evaluate accuracy and practical generalization of these techniques. Finally, the results of experimental study of all the method using common data was given to demonstrate the accuracy and complexity. This paper may serve as a stepping stone for future researchers in cross-disciplinary field of machine learning aided malware forensics.