Explicabilidade de Modelos de Aprendizado de Máquina para Sistemas de Detecção de Intrusão em Redes IoT Usando Fluxo Agregado

With the increasing use of connected devices in Internet of Things (IoT) networks, concerns regarding cybersecurity have also grown. This work presents a machine learning-based methodology for cyberattack detection using aggregated network flow data. The CICIoT2023 dataset was employed to evaluate the proposed approach. The results demonstrated effective malicious traffic detection using only flow information. Furthermore, Explainable Artificial Intelligence (XAI) techniques were applied to interpret the models and identify relevant features for attack detection, highlighting the potential of the approach for Intrusion Detection Systems (IDS).