RansomWare Detection And Mitigation

Ransomware Detection and Mitigation: A Systematic Survey of Machine Learning, Deep Learning, and Blockchain-Based Approaches This research paper presents a systematic survey of 18 studies on ransomware detection, classification, and mitigation published between 2019 and 2026. It examines machine learning and deep learning techniques, behavioral analysis, blockchain-based cryptocurrency transaction tracing, and security approaches for cloud computing, industrial control systems, healthcare, and IoT environments. The study compares existing methods based on their techniques, datasets, strengths, and limitations. It identifies key research challenges, including detecting zero-day and obfuscated ransomware, the lack of updated and representative datasets, high computational overhead, and inconsistent evaluation metrics. Finally, it proposes future research directions focused on lightweight detection models, improved datasets, standardized evaluation protocols, and enhanced blockchain forensics to strengthen cybersecurity against evolving ransomware threats.