EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-Based User-Level Anomaly Detection in Internet Service Providers Using Unsupervised Learning

Saif Ullah, S.M.A. Motakabber, Othman Omran Khalifa, Jia Uddin

International Journal on Advanced Science, Engineering and Information Technology · 15.10.2026 · 16 (5) · 1584-1593

DOI: 10.18517/ijaseit.16.5.21977 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal on Advanced Science, Engineering and Information Technology, online erschienen am 15.10.2026. Verfasst von Saif Ullah und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Detecting user-level anomalies in Internet Service Provider (ISP) networks is difficult because labeled ground truth is unavailable, and single-model decisions are rarely stable. Identifying long-term abnormal behavior is even harder because user activity patterns change continuously in operational environments. In this study, we present a consensus-based analysis mechanism for user-level anomaly detection using real operational network logs, including 546,277 event-level records from 398 users. We characterized user activity using aggregated metadata statistics. These included event volume, port diversity, and packet length measures. We applied three unsupervised learning techniques: Autoencoder, Isolation Forest, and One-Class Support Vector Machine (SVM). We combined their outputs through a two-out-of-three majority voting scheme to produce the final anomaly decision. The results show that each model identifies anomalies differently, with rates ranging from 1.01% to 4.52%. The suggested consensus technique reduced the final anomaly rate to 0.75%, showing more reliable decisions and less bias against specific models. The agreement-based evaluation showed that the Autoencoder was the most in line with the final consensus decision, with a Cohen kappa value of 0.856. SHapley Additive exPlanations (SHAP) and Model-Agnostic Explanations (LIME) were used to identify the most important features for anomaly detection: packet length characteristics and port variety. The suggested framework offers a scalable, flexible, and understandable method for metadata-based monitoring in real ISP networks.

Zitieren

APA

Ullah, S., Motakabber, S., Khalifa, O. O., & Uddin, J. (2026). AI-Based User-Level Anomaly Detection in Internet Service Providers Using Unsupervised Learning. International Journal on Advanced Science, Engineering and Information Technology, 16(5), 1584-1593. https://doi.org/10.18517/ijaseit.16.5.21977

Vancouver

Ullah S, Motakabber S, Khalifa OO, Uddin J. AI-Based User-Level Anomaly Detection in Internet Service Providers Using Unsupervised Learning. International Journal on Advanced Science, Engineering and Information Technology. 2026;16(5):1584-1593. doi:10.18517/ijaseit.16.5.21977

BibTeX
@article{Ullah2026,
  author = {Ullah, Saif and Motakabber, S.M.A. and Khalifa, Othman Omran and Uddin, Jia},
  title = {AI-Based User-Level Anomaly Detection in Internet Service Providers Using Unsupervised Learning},
  journal = {International Journal on Advanced Science, Engineering and Information Technology},
  year = {2026},
  volume = {16},
  number = {5},
  pages = {1584--1593},
  doi = {10.18517/ijaseit.16.5.21977}
}
Kostenlos starten →