Comparative Analysis of Supervised Machine Learning Models for Ransomware Detection

Ransomware attacks have emerged as one of the most disruptive threats in our cyber world, encrypting victims data before demanding ransom payments to decrypt and restore the data. Traditional security measures cannot keep pace with the dynamic nature of ransomware attacks. Over the past few years, supervised learning techniques have been established as potential methods for identifying and controlling ransomware harm. This study compares supervised machine learning techniques for ransomware detection by analyzing their performance, datasets, and key detection parameters.. We also cover popular classification algorithms, feature selection techniques, and evaluation metrics, outlining their advantages and disadvantages. Moreover, this study investigates real-world datasets used in research and highlights the shortcomings of current detection approaches. The results highlight the capability of machine learning for proactive ransomware mitigation while overcoming challenges such as dataset reliability and model interpretability.