EUVIMEDEUVIMED entdecken
Crossref

Behavioral Pattern Analysis for Cyber Threat Detection Application of Support Vector Regression and AdaBoost in Network Security Monitoring

Naidu Paila

Journal of Secure Software and Cloud Data Protection Technologies · 2026 · 1 (1) · 1-9

DOI: 10.55124/jcds.v1i1.103 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Secure Software and Cloud Data Protection Technologies, 2026. Verfasst von Naidu Paila.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of digital infrastructure more sophisticated threats. Legacy signature-based detection and traditional firewalls are fighting back against attacks using AI, machine learning, and automation. This study addresses the need for advanced detection by using machine learning to predict threats from network traffic, login attempts, malware signature scores, and threat levels. We evaluate Support Vector Regression (SVR) and AdaBoost Regression (ABR) on a dataset of 100 incidents to examine the relationships between network behavior and threat severity. A strong positive correlation (0.94) between malware signature scores and threat levels supports the value of behavioral analysis. SVR provided the best results (R² = 0.9676 train, 0.9737 test; RMSE ≈ 5.32 train, 5.70 test). ABR performed well (R² = 0.9732 train, 0.9404 test), indicating strong generalization. Modern AI-powered cybersecurity solutions report 80– 92% efficiency, which is much higher than traditional systems (30–60%). Integrating AI enables real-time detection, automated responses, and proactive defenses. This research improves predictive intrusion detection, providing validated algorithmic tools to better assess and mitigate insider threats, APTs, and other complex cyberattacks that pose a risk to data integrity, financial, and regulatory compliance. Keywords: Cybersecurity threat detection; Machine learning algorithms; Support vector resilience; AdaBoost resilience; Artificial intelligence in cybersecurity.

Zitieren

APA

Paila, N. (2026). Behavioral Pattern Analysis for Cyber Threat Detection Application of Support Vector Regression and AdaBoost in Network Security Monitoring. Journal of Secure Software and Cloud Data Protection Technologies, 1(1), 1-9. https://doi.org/10.55124/jcds.v1i1.103

Vancouver

Paila N. Behavioral Pattern Analysis for Cyber Threat Detection Application of Support Vector Regression and AdaBoost in Network Security Monitoring. Journal of Secure Software and Cloud Data Protection Technologies. 2026;1(1):1-9. doi:10.55124/jcds.v1i1.103

BibTeX
@article{Paila2026,
  author = {Paila, Naidu},
  title = {Behavioral Pattern Analysis for Cyber Threat Detection Application of Support Vector Regression and AdaBoost in Network Security Monitoring},
  journal = {Journal of Secure Software and Cloud Data Protection Technologies},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {1--9},
  doi = {10.55124/jcds.v1i1.103}
}
Kostenlos starten →