article · Nature Journal of Emerging Sciences Technologies and Innovations
This research introduces an Anti-Ransomware File Backup System designed to combat the significant threat of ransomware attacks. The system integrates real-time detection using machine learning for behavioural analysis, dual-database protection with SSD-level and cloud-isolated backups for rapid recovery, and structured user education. It addresses common challenges in ransomware mitigation, such as balancing detection accuracy with system performance, securing backup systems, and human vulnerabilities. Experimental evaluation showed high detection accuracy and precision, near-instantaneous failover, and reduced user susceptibility to phishing, highlighting the importance of combining technical and human-centric defences for comprehensive ransomware resilience.
Ransomware poses a major threat to organisations, leading to data loss and financial damage. This research offers a comprehensive solution that not only detects and recovers from attacks but also educates users, significantly enhancing overall cyber resilience. Protecting critical data is vital for business continuity and security.
This research presents an applied system for mitigating ransomware attacks, suitable for organisations across critical sectors. It could be developed into a security product offering real-time protection, rapid data recovery, and integrated user training. The system appears to be at an advanced stage of research, with experimental evaluation demonstrating its effectiveness, suggesting it is near-market for deployment in enterprise environments.
AI-generated from the published abstract. Always read the original work before citing.
Ransomware has emerged as one of the most destructive cyber threats, causing extensive data loss, operational disruption, and financial damage across critical sectors. This research proposes an Anti-Ransomware File Backup System designed to mitigate the impact of ransomware attacks through the integration of real-time detection, dual-database protection, and structured user education. The system employs machine learning–based behavioral analysis to identify ransomware activity at an early stage, while leveraging SSD-level and cloud-isolated backups to ensure rapid recovery and data continuity. Key challenges in existing mitigation strategies, such as the trade-off between detection accuracy and system performance, backup system vulnerability, and the neglect of human factors, are addressed through a unified framework. Experimental evaluation demonstrates effective detection accuracy of about 99% and 99.5% precision with 591 true positives out of 600 and 597 true negatives out of 600, near-instantaneous failover, and significant reduction in user susceptibility to phishing-based attacks. The findings highlight the importance of combining technical defenses with user awareness to achieve end-to-end ransomware resilience. Recommendations for future work include hybrid detection models, edge-device optimization, and improved explainability of machine learning decisions.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.65752/smy3jb37
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
