A Hybrid Multi-Model Framework for Personalized User-Level Anomaly Detection with Data-Driven Threshold Optimization
Computation · 30.04.2026 · 14 (5) · 102
DOI: 10.3390/computation14050102 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computation, online erschienen am 30.04.2026. Verfasst von Amit Kumar und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Modern user authentication systems increasingly need user and device-behavior-aware adaptive mechanisms to detect evolving threats beyond the traditional authentication framework of static credential verification. This paper proposes a hybrid multi-model framework for personalized user-level anomaly detection using a data-driven Hybrid Anomaly Score (HAS). The primary contribution lies in deriving the HAS using the joint integration of three adaptive attributes: dynamically computed per-user deviation thresholds conditioned on individual behavioral history, profile-age-aware baseline weights reflecting user cohort maturity, and criticality-scaled aggregation with the security impact of each detection methodology. The framework is evaluated on a large-scale real-world dataset and demonstrates strong detection performance, while achieving low inference latency suitable for real-time enterprise deployment. The ablation analysis of the framework confirms that dynamic weighting and personalized threshold substantially improve detection stability and convergence with an effective and deployable solution for large-scale authentication environments.
Zitieren
APA
Kumar, A., Ahmad, W., Pal, O., & Sunil (2026). A Hybrid Multi-Model Framework for Personalized User-Level Anomaly Detection with Data-Driven Threshold Optimization. Computation, 14(5), 102. https://doi.org/10.3390/computation14050102
Vancouver
Kumar A, Ahmad W, Pal O, Sunil. A Hybrid Multi-Model Framework for Personalized User-Level Anomaly Detection with Data-Driven Threshold Optimization. Computation. 2026;14(5):102. doi:10.3390/computation14050102
BibTeX
@article{Kumar2026,
author = {Kumar, Amit and Ahmad, Wakar and Pal, Om and Sunil},
title = {A Hybrid Multi-Model Framework for Personalized User-Level Anomaly Detection with Data-Driven Threshold Optimization},
journal = {Computation},
year = {2026},
volume = {14},
number = {5},
pages = {102},
doi = {10.3390/computation14050102}
}
EUVIMED