A Machine Learning Approach for Malware Detection in Database Systems
Engineering, Technology & Applied Science Research · 06.06.2026 · 16 (3) · 36514-36522
DOI: 10.48084/etasr.18568 ↗Kurz gefasst
Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 06.06.2026. Verfasst von Abdulalem Ali und 4 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The proliferation of malware over the past decade has resulted in significant business losses for many organizations. The increasing speed, volume, and complexity of malware make it progressively more difficult for the anti-malware community to detect and eliminate threats. In recent years, researchers and antivirus companies have begun applying Machine Learning (ML) and Deep Learning (DL) methods to malware recognition and analysis. This study proposes the Machine Learning Approach to Detect Malware in Database Systems (MLADMDBS), an ML-based malware detection system for databases. The proposed system employs a two-phase framework that combines offline model training with online real-time detection. The Random Forest classifier, trained on 18 handcrafted features derived from SQL queries and user-behavior data, achieves high performance on a temporally separated test set of 3,000 database activities, with accuracy, precision, and recall exceeding 99.8%. These results, obtained on a controlled synthetic dataset, represent an upper-bound estimate; real-world performance on production traffic is expected to differ and will be validated in future work. Per-attack-type analysis confirms strong detection across SQL injection, data exfiltration, and database structure manipulation categories. With an average inference latency of 0.8 ms per query, the system is well-suited for real-time monitoring of database activity and automated threat response.
Zitieren
APA
Ali, A., Al-Dhaqm, A., Jhanjhi, N., Razak, S. A., & Bamasoud, D. M. (2026). A Machine Learning Approach for Malware Detection in Database Systems. Engineering, Technology & Applied Science Research, 16(3), 36514-36522. https://doi.org/10.48084/etasr.18568
Vancouver
Ali A, Al-Dhaqm A, Jhanjhi N, Razak SA, Bamasoud DM. A Machine Learning Approach for Malware Detection in Database Systems. Engineering, Technology & Applied Science Research. 2026;16(3):36514-36522. doi:10.48084/etasr.18568
BibTeX
@article{Ali2026,
author = {Ali, Abdulalem and Al-Dhaqm, Arafat and Jhanjhi, NZ and Razak, Shukor Abd and Bamasoud, Doaa M.},
title = {A Machine Learning Approach for Malware Detection in Database Systems},
journal = {Engineering, Technology & Applied Science Research},
year = {2026},
volume = {16},
number = {3},
pages = {36514--36522},
doi = {10.48084/etasr.18568}
}
EUVIMED