2026-06-30T05:57:54Zhttps://riubu.ubu.es/oai/request

oai:riubu.ubu.es:10259/118602026-06-19T05:15:47Zcom_10259_3847com_10259_5086com_10259_2604com_10259_8983col_10259_3848col_10259_8984

Martin Reizabal, Sergio e819e710-072a-4348-9ddf-9968fa1de0fb 600 Caballero Quiroga, Adrian e4f2b3fa-1786-47b8-9d2a-e3c113a9f35c Gil Arroyo, Beatriz 946 600 0009-0009-8499-093X Basurto Hornillos, Nuño 742 600 0000-0001-7289-4689 Ruiz González, Rubén 735 600 0000-0001-7006-2395 2026-06-18T10:16:23Z 2026-06-18T10:16:23Z 2026-03 2542-6605 https://hdl.handle.net/10259/11860 10.1016/j.iot.2026.101879 The explosive growth of the IoT has led to an increasingly complex and heterogeneous network traffic, posing major challenges for intrusion detection. Most existing machine learning and deep learning approaches model network traffic at the level of individual flows, which limits their ability to capture contextual relationships among concurrent communications. This paper introduces a Transformer-based framework for IoT intrusion detection that aggregates network flows into fixed-duration windows and treats each flow as a token within the input sequence. The self-attention mechanism captures contextual relationships among concurrent flows, enabling effective modeling of temporal dependencies without recurrence. Experiments conducted on the CICIoT2023 dataset show that the proposed model achieves a weighted F1-score of 97.9% and a macro ROC–AUC of 99.6% under temporally blocked cross-validation, while maintaining high computational efficiency. These results demonstrate that flow-to-window aggregation combined with self-attention provides a robust and scalable foundation for IoT network security, suitable for deployment in edge and smart-home environments. eng Elsevier Internet of Things. 2026, V. 36, art. 101879 https://doi.org/10.1016/j.iot.2026.101879 Atribución-NoComercial 4.0 Internacional http://creativecommons.org/licenses/by-nc/4.0/ info:eu-repo/semantics/openAccess Internet of things (IoT) Network traffic classification Intrusion detection system (IDS) Transformer Self-attention Deep learning Internet de los objetos Computación ubicua Internet of things Ubiquitous computing Transformer-based classification of IoT network traffic with flow-to-window aggregation info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Internet of Things 36 101879 THUMBNAIL Martín-IoT_2026.pdf.jpg Martín-IoT_2026.pdf.jpg IM Thumbnail image/jpeg 4889 https://riubu.ubu.es/bitstream/10259/11860/4/Mart%c3%adn-IoT_2026.pdf.jpg 805cdc43aef72af5faa6f9bff6200788 MD5 4 LICENSE license.txt license.txt text/plain; charset=utf-8 1362 https://riubu.ubu.es/bitstream/10259/11860/3/license.txt 5d013bfa6e473ff0db22cd82a4d71a70 MD5 3 CC-LICENSE license_rdf license_rdf application/rdf+xml; charset=utf-8 914 https://riubu.ubu.es/bitstream/10259/11860/2/license_rdf 24013099e9e6abb1575dc6ce0855efd5 MD5 2 ORIGINAL Martín-IoT_2026.pdf Martín-IoT_2026.pdf application/pdf 4754415 https://riubu.ubu.es/bitstream/10259/11860/1/Mart%c3%adn-IoT_2026.pdf 27aa2ac623bc049e20b6a5b3f47693f1 MD5 1 10259/11860 oai:riubu.ubu.es:10259/11860 2026-06-19 07:15:47.875 Repositorio Institucional de la Universidad de Burgos bubrep@ubu.es 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