A Comprehensive Review of Machine Learning-Based Malware Detection Techniques for Windows Platform

Abstract

The growing threat of windows malware poses an increasing risk to the security of computers and the sensitive information they hold. The exponential rise in malware threats targeting the windows platform necessitates robust and adaptive detection mechanisms. Machine learning (ML) techniques demonstrate effectiveness in identifying windows malware therefore, a thorough analysis of these techniques is essential. This paper presents a comprehensive review of machine learning based techniques which have been proposed by research community for detecting windows malware. The review begins by providing a comparison of this study with the existing reviews. Then, we provide details of different ML based malware detection techniques. These techniques have been assessed on multiple parameters including: dataset used for training and testing, availability of dataset, ML model used for classification, the type of extracted features, analysis type and the metrics employed to measure the effectiveness of technique. Furthermore, the paper highlights the limitations and challenges in this field and suggests potential future research directions. By providing a comprehensive overview and critical analysis of ML-based malware detection techniques proposed for the windows environment, this study aims to guide and inspire further research in handling evolving cyber threats.

Keywords

• malware detection
• windows platform
• machine learning