SQL Server Security Hardening Using AI-Based Threat Detection Models
Multidisciplinary Studies and Innovative Research · 10.06.2023 · 4 (2) · 1-16
DOI: 10.65923/g9arv591 ↗Kurz gefasst
Fachartikel in der Zeitschrift Multidisciplinary Studies and Innovative Research, online erschienen am 10.06.2023. Verfasst von Chandrakanth Reddy Borra.
Abstract (Originalsprache)
SQL Server remains one of the most widely deployed relational database management systems (RDBMS) in enterprise environments, storing highly sensitive organizational and customer data. Despite built-in security features, SQL Server instances continue to face advanced cyber threats such as SQL injection, privilege escalation, and insider attacks. Traditional security hardening techniques, including configuration best practices and patch management, provide baseline protection but fail to dynamically detect emerging threats. This paper proposes an AI-based threat detection model for SQL Server environments that continuously monitors server activities, database access patterns, and configuration changes to identify potential security risks. By leveraging machine learning algorithms and anomaly detection techniques, the framework automates threat detection, reduces reliance on manual monitoring, and supports proactive SQL Server hardening. Experimental results demonstrate that AI-based monitoring enhances detection accuracy, identifies previously unseen threats, and improves the overall security posture of SQL Server instances.
Zitieren
APA
Borra, C. R. (2023). SQL Server Security Hardening Using AI-Based Threat Detection Models. Multidisciplinary Studies and Innovative Research, 4(2), 1-16. https://doi.org/10.65923/g9arv591
Vancouver
Borra CR. SQL Server Security Hardening Using AI-Based Threat Detection Models. Multidisciplinary Studies and Innovative Research. 2023;4(2):1-16. doi:10.65923/g9arv591
BibTeX
@article{Borra2023,
author = {Borra, Chandrakanth Reddy},
title = {SQL Server Security Hardening Using AI-Based Threat Detection Models},
journal = {Multidisciplinary Studies and Innovative Research},
year = {2023},
volume = {4},
number = {2},
pages = {1--16},
doi = {10.65923/g9arv591}
}
EUVIMED