Adaptive Hybrid Framework for IIoT Intrusion Detection Yields Robust Solution

Strategic Insights -

Researchers at Taibah University have developed an adaptive hybrid framework for Industrial Internet of Things (IIoT) intrusion detection that combines Artificial Neural Networks (ANNs) with Genetic Algorithms (GA) for feature optimization. This innovative approach provides a robust solution for real-time IIoT security, outperforming conventional detection systems. The study utilized a widely recognized benchmark dataset, comprising 625,783 network traffic samples, and achieved a 99.7% validation accuracy with an AUC score of 0.9969. The proposed framework demonstrated exceptional robustness, achieving 99.5% accuracy on the test set, with precision and recall values of 0.97 and 0.98, respectively.

Key Takeaways:

  • The researchers developed an adaptive hybrid framework for IIoT intrusion detection that combines ANNs with GA for feature optimization, achieving a 99.7% validation accuracy with an AUC score of 0.9969.
  • The proposed framework utilized a widely recognized benchmark dataset comprising 625,783 network traffic samples, classified into five categories: Denial-of-Service (DoS), Probe, Remote-to-Local (R2L), User-to-Root (U2R), and Normal traffic.
  • The study introduced L2 regularization, adjusted dropout rates, and optimized the learning rate to enhance generalization and computational efficiency without sacrificing predictive power.
  • The proposed model demonstrated exceptional robustness, achieving 99.5% accuracy on the test set, with precision and recall values of 0.97 and 0.98, respectively.
  • The combination of ANNs and GA yielded a highly efficient and sensitive framework, providing enhanced detection of anomalies in IIoT environments.
  • The proposed framework outperformed conventional detection systems through a strategic blend of neural learning and evolutionary optimization.
  • Mohammad Zubair Khan, Dr. Aijaz Ahmad Reshi, Shabana Shafi, and Ibrahim Aljubayri contributed to the research, with Mohammad Zubair Khan serving as the lead author.

Statistics:

  • The dataset utilized in the study comprises 625,783 network traffic samples, classified into five categories.
  • The proposed framework achieved a 99.7% validation accuracy with an AUC score of 0.9969.
  • The model demonstrated exceptional robustness, achieving 99.5% accuracy on the test set.
  • The precision value achieved by the model was 0.97, while the recall value was 0.98.

Sources:

  • An adaptive hybrid framework for IIoT intrusion detection using neural networks and feature optimization using genetic algorithms. Discover Sustainability, 2025,6(1):1-20. (Springer)
  • NewsRx. New Sustainability Research Study Findings Reported from Taibah University (An adaptive hybrid framework for IIoT intrusion detection using neural networks and feature optimization using genetic algorithms). Life Science Weekly. May 27, 2025; p 2676.