Real-Time Ransomware Detection Using Visual Analytics and Adaptive Machine Learning
Research Digest on Engineering Management and Social Innovations · 23.06.2026 · 2 (6)
DOI: 10.46647/rdems0206014 ↗Kurz gefasst
Fachartikel in der Zeitschrift Research Digest on Engineering Management and Social Innovations, online erschienen am 23.06.2026. Verfasst von mallikarjuna mangala und 1 weiteren Autor:innen.
Abstract (Originalsprache)
The rapid evolution of polymorphic ransomware variants demands a shift from passive signature-based defenses to immediate runtime tracking paradigms. This paper proposes an integrated real-time ransomware detection and mitigation framework that unifies adaptive multi- modal machine learning with an interactive visual analytics control layer. By continuously evaluating runtime events across file systems, registry changes, and network patterns, our architecture monitors security conditions at critical attack milestones. We construct a multi-stage stacking ensemble model leveraging Random Forest, XGBoost, and a 1D Convolutional Neural Network layered with a Self-Attention channel to register long-term inter-process operation signatures. To validate scalability, extensive empirical evaluations were completed across a comprehensive pool of 15,000 verified ransomware signatures from 42 core structural families paired with 10,000 baseline benign records. The adaptive processing scheme delivers a 98.7% classification precision rate, a 0.8% false positive benchmark, and an operational system traversal execution speed of 2.3 seconds per validation pass. By interfacing structural tracking with nested real-time heatmaps, process graph configurations, and chronological layout controls, this setup alleviates cognitive alert burdens for enterprise operations teams while reinforcing operational network environments against zero-day execution threats
Zitieren
APA
mangala, M., & Mangapoti, M. (2026). Real-Time Ransomware Detection Using Visual Analytics and Adaptive Machine Learning. Research Digest on Engineering Management and Social Innovations, 2(6). https://doi.org/10.46647/rdems0206014
Vancouver
mangala M, Mangapoti M. Real-Time Ransomware Detection Using Visual Analytics and Adaptive Machine Learning. Research Digest on Engineering Management and Social Innovations. 2026;2(6). doi:10.46647/rdems0206014
BibTeX
@article{mangala2026,
author = {mangala, mallikarjuna and Mangapoti, Maneedeep},
title = {Real-Time Ransomware Detection Using Visual Analytics and Adaptive Machine Learning},
journal = {Research Digest on Engineering Management and Social Innovations},
year = {2026},
volume = {2},
number = {6},
doi = {10.46647/rdems0206014}
}
EUVIMED