ERBAM:Effective Ransomware Behavior Analysis and Mitigation
International Journal of Creative and Open Research in Engineering and Management · 03.05.2026 · 02 (05) · 1-10
DOI: 10.55041/ijcope.v2i5.001 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Creative and Open Research in Engineering and Management, online erschienen am 03.05.2026. Verfasst von Suleman Luswal Suleman Luswal und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Ransomware attacks have become increasingly sophisticated, causing severe financial and data losses across various sectors. Traditional antivirus and signature based defenses fail to detect new or evolving ransomware strains due to their dynamic behavior. This is our aim to analyze the behavioral patterns of ransomware in real time. Traditional signature-based antivirus systems are increasingly ineffective against modern ransomware due to polymorphic code structures, fileless execution, and zero-day attack strategies. This research proposes Adaptive Pattern Signature Analysis (APSA), a behavior-driven ransomware detection framework designed to identify malicious activity through dynamic behavioral analysis rather than static signatures. The APSA framework introduces a multi-layer detection architecture that continuously analyzes system activity using behavioral indicators such as encryption frequency, anomalous file access patterns, network communication irregularities, and abnormal CPU or resource utilization. These features are modeled through statistical anomaly detection using Z-score normalization, Mahalanobis distance, and probabilistic risk estimation, allowing the system to capture coordinated deviations across multiple behavioral dimensions. A weighted scoring mechanism combined with a sigmoid-based probabilistic decision model enables APSA to classify processes into four threat levels: Clean, Monitor, Suspicious, and Alert. Unlike conventional systems that rely heavily on predefined malware signatures, APSA dynamically updates behavioral baselines using adaptive learning techniques, allowing the model to evolve alongside emerging ransomware variants. Experimental validation using multiple malware datasets demonstrates that APSA achieves 96.3% detection accuracy, 94.8% precision, and 95.2% recall, while maintaining a low 1.2% false positive rate and an average 2.3-second detection latency. The proposed framework offers a scalable and proactive defense mechanism capable of detecting sophisticated ransomware attacks, including cryptojacking and fileless malware. By integrating adaptive learning with probabilistic threat scoring, APSA contributes toward the development of next-generation intelligent cybersecurity defense systems. Index Terms - Ransomware Behavior Analysis,APSA Framework,Adaptive Matching Engine,Real-time Threat Detection.
Zitieren
APA
Luswal, S. L. S., Awaze, A., khan, M. A. K. M. A., rajagopal, S. R. S., & Fahad, G. A. F. G. A. (2026). ERBAM:Effective Ransomware Behavior Analysis and Mitigation. International Journal of Creative and Open Research in Engineering and Management, 02(05), 1-10. https://doi.org/10.55041/ijcope.v2i5.001
Vancouver
Luswal SLS, Awaze A, khan MAKMA, rajagopal SRS, Fahad GAFGA. ERBAM:Effective Ransomware Behavior Analysis and Mitigation. International Journal of Creative and Open Research in Engineering and Management. 2026;02(05):1-10. doi:10.55041/ijcope.v2i5.001
BibTeX
@article{Luswal2026,
author = {Luswal, Suleman Luswal Suleman and Awaze, Awaze and khan, Musahib Ali khan Musahib Ali and rajagopal, smitha rajagopal smitha and Fahad, Gounda Areeb Fahad Gounda Areeb},
title = {ERBAM:Effective Ransomware Behavior Analysis and Mitigation},
journal = {International Journal of Creative and Open Research in Engineering and Management},
year = {2026},
volume = {02},
number = {05},
pages = {1--10},
doi = {10.55041/ijcope.v2i5.001}
}
EUVIMED