Esteban Martínez, AlejandroEsteban Martínez, DavidGuijarro-Berdiñas, BerthaAlonso-Betanzos, AmparoHernández-Pereira, ElenaHernández-Castro, Julio2026-09-102026-09-102024D. Esteban Martínez, B. Guijarro-Berdiñas, A. Alonso Betanzos, E. Hernández-Pereira, and A. Esteban Martínez, "AI-based Algorithm for Intrusion Detection on a Real Dataset", ESANN 2024 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges (Belgium), 2024, pp. 215-220, https://doi.org/10.14428/ESANN/2024.ES2024-204978-2-87587-090-2https://hdl.handle.net/2183/49191Presented at: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2024), October 9 - 11, 2024, Bruges (Belgium). Available at: https://www.esann.org/proceedings/2024[Abstract]: In the realm of cybersecurity, the detection of network intrusions stands as a paramount challenge, with ever-evolving threats demanding innovative solutions. This study delves into the application of diverse machine learning algorithms on a contemporary dataset (UGR'16) comprising real-world instances of intrusion in software systems. Specifically, several Machine Learning models (Outlier Detectors, Ensemble Methods, Deep Learning, and Conventional Classifiers) were tested and compared with previously reported results using a standard methodology. The obtained results reveal that the Ensemble Methods have been capable of improving the results from prior research. Particularly, the Extreme Gradient Boosting (XGBoost) algorithm offers better results than the original solution with Random Forest, with an AUC of 0.9218 as opposed to 0.8977, and more than four times as fast for the problem to solve.eng© ESANN 2024. All rights reserved. This is the published version of the paper, distributed in accordance with ESANN's self-archiving policy, which allows authors to archive their work in any repository provided that full reference is made to the ESANN publication.Machine learningIntrusion detection systemEnsemble methodsComputer network attacksDeep learningOutlier detectionconference outputopen access10.14428/ESANN/2024.ES2024-204