Federated Deep Learning Models for Intrusion Detection in IoT
El Mahfoud Ennaji, Salah El Hajla, Yassine Maleh, Soufyane Mounir · 2024
In response to the escalating transmission of sensitive data within IT infrastructures, healthcare organizations, and entities generating wearable user data have become susceptible targets for cyber threats. Securing electronic data in Internet of Things (IoT) devices necessitates the implementation of robust Intrusion Detection Systems (IDS) to ensure a secure environment. Our proposal focuses on enhancing attacks detection in IoT devices through the implementation of federated learning. This innovative approach allows the model to learn from decentralized data sources without compromising user privacy. The evaluation of the detection performance employs metrics such as accuracy and precision. The proposed Deep Federated Learning model is validated using the Edge-IIoTset dataset, achieving an accuracy rate of 90% in the detection of attacks