Abstract
Ransomware has emerged as one of the most pervasive and destructive threats in the realm of cybersecurity, targeting individuals, businesses, and institutions globally. Traditional antivirus solutions often fall short in detecting sophisticated ransomware variants due to their reliance on signature-based approaches. This study proposes an automated ransomware detection and classification framework leveraging supervised machine learning models. The framework extracts key features from network traffic and file behaviors to train models capable of accurately distinguishing ransomware from benign software. Comparative analysis of algorithms such as Random Forest, Support Vector Machines, and Gradient Boosting highlights their performance in terms of accuracy, precision, recall, and F1-score. Results demonstrate that machine learning significantly enhances the detection and classification of ransomware, offering real-time solutions for mitigating this cyber threat. The proposed system is poised to contribute to more robust and adaptive cybersecurity strategies in combating ransomware attacks.