Systematic literature review on malware detection using Explainable Machine Learning (XAI)

The advancement of malware detection through machine learning and deep learning has been extensively explored. However, the models produced by these methods are still considered opaque and require scrutiny to ensure they do not present a threat, particularly in sensitive applications. This study aims to investigate various scholarly sources on the development of interpretable machine learning frameworks for malware detection, encompassing 28 chosen papers for review. The goal is to pinpoint areas for further research into interpretable machine learning approaches for detecting malware. The methodology involves systematic literature review techniques comprising question formulation, research strategy, study selection, quality assessment, data extraction, synthesis, analysis and presentation. The findings will assist security system analysts in safeguarding systems against sophisticated forms of malware currently beyond existing capabilities.