Use this link to cite:
https://hdl.handle.net/2183/50184 Building a Supervised–Unsupervised Ensemble for Intrusion Detection Systems Using Model Calibration and Decision Fusion
Loading...
Identifiers
Publication date
Authors
Advisors
Other responsabilities
Journal Title
Bibliographic citation
Á.Lagares Vázquez, D. Garabato, V. Carneiro, D. Fernández Iglesias, F. Cacheda, F. J. Nóvoa, "Building a Supervised–Unsupervised Ensemble for Intrusion Detection Systems Using Model Calibration and Decision Fusion", Computer Networks, Vol. 292, 112905, Jan. 2027, https://doi.org/10.1016/j.comnet.2026.112905
Type of academic work
Academic degree
Abstract
[Abstract] Machine learning, particularly deep learning, has become a prominent approach to network intrusion detection because it can learn patterns from network traffic and adapt to evolving threats. However, most existing Intrusion Detection Systems (IDS) approaches address only one side of the problem: they either classify known attacks from labeled data or detect previously unseen attacks through anomaly detection. In operational network environments, both capabilities are required within a single adaptive system. To address this limitation, we propose a hybrid IDS that combines supervised and unsupervised models in a calibration-aware ensemble designed to detect both known attacks and attack classes absent from the training data. The main contribution of this work is a calibration and decision fusion pipeline that aligns the outputs of heterogeneous models and integrates them into a unified detection decision. Experiments conducted using two benchmark datasets, CIC-IDS2017 and BoT-IoT, across different experimental settings, show that the proposed ensemble is capable of both detecting previously unseen attacks and performing multiclass classification of known attacks, while maintaining comparable multiclass performance despite the increased task complexity. It also improves binary detection performance, indicating that the hybrid design successfully exploits the complementary strengths of supervised classification and unsupervised anomaly detection.
Description
Financiado para publicación en acceso aberto: Universidade da Coruña/CISUG
Editor version
Rights
Attribution-NonCommercial 4.0 International








