Enhancing Mac OS Malware Detection through Machine Learning and Mach-O File Analysis

Malware research has predominantly focused on Windows and Android Operating Systems (OS), leaving Mac OS malware relatively unexplored. This paper addresses the growing threat of Mac OS malware by leveraging Machine Learning (ML) techniques. We propose a novel system for Mac malware detection that extends beyond traditional executables to include various Mach-O (Mach Object) file types. Our research encompasses feature selection, data sets, and the implementation of ML classifiers. We meticulously evaluate system performance using Precision, Recall, F1 score, and Accuracy metrics. Our findings highlight the challenges and opportunities in Mac malware detection and provide valuable insights for future research.