Sign in Subscribe
Privacy

Hybrid Federated Ensemble Learning Framework for Intrusion Detection in IoT Networks

Strategic Insights

— 1 min read

A new study on Information Technology and Data Privacy has introduced a novel Hybrid Federated Ensemble Learning (HFEL) framework that combines the benefits of federated learning with the robust detection capabilities of ensemble methods. The research, published in Cluster Computing, demonstrates that HFEL significantly outperforms traditional federated learning approaches in detecting cyber-attacks while preserving data privacy. The framework integrates three complementary models, Multi-Layer Perceptron, Random Forest, and XGBoost, and utilizes majority voting for final decision-making.

Key Takeaways:

  • The HFEL framework is designed to address the security challenges introduced by IoT networks, particularly in detecting and preventing cyber-attacks while preserving data privacy.
  • The framework combines the privacy-preserving benefits of federated learning with the robust detection capabilities of ensemble methods.
  • The experimental results demonstrate that HFEL achieves 99.94% accuracy on the BoT-IoT dataset and 97.53% on the Edge-IIoT dataset, outperforming traditional federated learning approaches.
  • HFEL addresses the cold-start problem common in federated learning systems, maintaining consistent performance from initial deployment.
  • Comparative analysis with state-of-the-art methods confirms HFEL's superior detection capabilities while preserving data privacy.
  • The research is particularly suitable for securing distributed IoT networks.
  • The authors of the study include Yassine Maleh, Salah El Hajla, El Mahfoud Ennaji, and Soufyane Mounir from Sultan Moulay Slimane University.

Statistics:

  • 99.94% accuracy on the BoT-IoT dataset
  • 97.53% accuracy on the Edge-IIoT dataset
  • 2 benchmark datasets used in the experimental evaluation: BoT-IoT and Edge-IIoT
  • 3 complementary models integrated in the HFEL framework: Multi-Layer Perceptron, Random Forest, and XGBoost

Sources:

  • Hfel: a Hybrid Federated Ensemble Learning Framework for Intrusion Detection In Iot Networks. Cluster Computing, 2025;28(13).
  • Cluster Computing, Springer. (www.springer.com; Cluster Computing - www.springerlink.com/content/1386-7857/)
  • NewsRx. Study Data from Sultan Moulay Slimane University Update Understanding of Information and Data Privacy (Hfel: a Hybrid Federated Ensemble Learning Framework for Intrusion Detection In Iot Networks). Information Technology Newsweekly. October 21, 2025; p 907.

Read more