RT dataset
T1 Labeled IoT Window-Based Random Network Pattern Dataset for Reinforcement Learning
A1 Rodríguez Villagrá, César
A1 Martin Reizabal, Sergio
A1 Ruiz González, Rubén
A1 Basurto Hornillos, Nuño
A1 Herrero Cosío, Álvaro
K1 Internet of things
K1 Cybersecurity
K1 Attack Traffic
K1 Benign traffic
K1 Network
K1 DDoS
K1 DoS
K1 Reinforcement learning
K1 Seguridad informática
K1 Computer security
K1 Aprendizaje automático
K1 Machine learning
AB This dataset is designed to support the training and evaluation ofreinforcement learning models in the context of network trafficanalysis. It is derived from an existing IoT network traffic dataset,from which packet capture (pcap) files were selected and processedfollowing a custom methodology explained in [MethodologicalInformation](methodological-information). The resulting datarepresentation is based on a windowing approach, where network trafficis segmented into fixed-size temporal windows.Each window aggregates traffic instances and is labeled according to itscomposition as benign, attack, or mixed (containing both benign andmalicious activity). The final datasets are generated through randomcombinations of these windows, enabling the creation of diverse trafficpatterns that better reflect dynamic and random network conditions.This structure facilitates the use of the dataset in reinforcementlearning scenarios, where agents must learn to identify, classify, orrespond to varying traffic behaviors over time. Additionally, theevaluation datasets are generated following the same methodology as thetraining datasets, but are kept separate and are not used during thetraining process, allowing for an independent evaluation of modelperformance.
PB Universidad de Burgos
YR 2026
FD 2026-04-12
LK https://hdl.handle.net/10259/11497
UL https://hdl.handle.net/10259/11497
LA eng
NO This publication is part of the AI4SECIoT project ("Artificial Intelligence for Securing IoT Devices"), funded by the National Cybersecurity Institute (INCIBE), derived from a collaboration agreement signed between the National Institute of Cybersecurity (INCIBE) and the University of Burgos. This initiative is carried out within the framework of the Recovery, Transformation and Resilience Plan funds, financed by the European Union (Next Generation), the project of the Government of Spain that outlines the roadmap for the modernization of the Spanish economy, the recovery of economic growth and job creation, for solid, inclusive and resilient economic reconstruction after the COVID19 crisis, and to respond to the challenges of the next decade.
DS Repositorio Institucional de la Universidad de Burgos
RD 22-abr-2026