The Recent Trends in Ransomware Detection and Behaviour Analysis

Ransomware attacks, with their evolving tactics and devastating impacts, have become one of the most critical threats in cybersecurity. This study provides a comprehensive analysis of recent advancements in ransomware detection and behavior analysis, focusing on trends from the last two years. Through an in-depth behavioral analysis of 14 ransomware families, the research highlights common infection vectors, encryption strategies, and malicious activities. Moreover, a comparative evaluation of publicly available and proprietary datasets reveals the challenges in training robust machine learning models. By analyzing 12 state-of-the-art detection methodologies, this research highlights the superiority of Random Forest-based models and the critical role of dynamic analysis techniques like API calls in early-stage detection. This research reveals a pressing need for real-time detection systems and localized solutions to prevent mass data encryption. This research aims to bring light to the ransomware research community, by addressing gaps in current methodologies and proposing future directions against the growing ransomware menace effectively.