Nieto Antelo, AdriánFernández, DiegoNóvoa, Francisco2023-11-082023-11-082023http://hdl.handle.net/2183/34111Cursos e Congresos , C-155[Abstract] In recent years, the complexity of threats utilizing the network as an attack vector has significantly increased. Traditional attack prevention and detection systems (IPS/IDS) based on signatures do not provide an acceptable level of security for many organizations. Furthermore, the volume of traffic on corporate networks has also grown exponentially, while quality of service requirements do not always allowfor deep inspection (at the application layer) of packets. The main objective of this work is to demonstrate that the application of machine learning techniques to the information of data flows circulating through the network allows for the satisfactory detection of malicious traffic. Specifically, this work is developed within an emerging network paradigm, such as software-defined networks.engAttribution 4.0 International (CC BY 4.0)https://creativecommons.org/licenses/by-nc-sa/4.0/deed.esAprendizaje automáticoFlujo de datosDetección de malwareInteligencia artificialconference outputopen access