Advancing Ransomware Mitigation Through Hybrid Models: A Systematic Literature Review

Abstract

Abstract—Ransomware, particularly Crypto-ransomware, poses a severe and evolving threat to corporate networks, causing significant financial and operational disruption. Traditional detection and mitigation techniques are increasingly inadequate in addressing the dynamic nature of these attacks. This systematic review explores intelligent hybrid models designed to proactively detect and mitigate crypto-ransomware threats within corporate environments. These models combined Machine Learning (ML) algorithms, Software-Defined Networking (SDN), and diverse security frameworks to enhance detection accuracy and response efficiency. We highlight how the combination of deep learning, signature-based techniques, and anomaly detection in hybrid frameworks improves overall responsiveness and effectiveness. The review also identifies key advancements in the field while outlining persistent challenges such as scalability, real-time implementation, and adaptability to evolving ransomware tactics. Based on our findings, we propose future research directions including: (1) the development of adaptive hybrid models with continuous learning capabilities for real-time threat adaptation, (2) the implementation of collaborative threat intelligence sharing via SDN and ML technologies across corporate networks, (3) the adoption of advanced deep learning architectures such as Long Short-Term Memory (LSTM) networks for accurate classification of ransomware behaviors, and (4) the design of scalable, SDN-based defense systems capable of handling high-traffic corporate environments. These recommendations aim to improve the efficacy and resilience of hybrid detection models in the face of modern ransomware threats.

Keywords- Crypto-ransomware, Intelligent hybrid models, Real-time anomaly detection, Software-Defined Networking (SDN), Deep Learning.