FeatNet-IDS: Anomaly Detection based-Features for Industrial Internet of Things Systems

Anomaly detection is critical for securing Industrial Internet of Things (IIoT) systems against evolving cyber threats. This paper introduces FeatNet-IDS, an enhanced Intrusion Detection System (IDS) for MQTT-based IIoT environments. FeatNet- IDS combines advanced feature selection and machine learning techniques to improve anomaly detection accuracy, efficiency, and interpretability. Evaluated on a domain-specific dataset of MQTT-related attacks, including control logic injection, the framework achieves 92.3% accuracy, 91.5% F1-score, and 96.8% ROC AUC, with a low false alarm rate of 2.73%. By emphasizing feature stability and importance, FeatNet-IDS outperforms or matches state-of-the-art methods, demonstrating robustness and transparency. Practical deployment implications are discussed, with future work addressing dataset expansion, hyperparameter tuning, and advanced ensemble approaches. The dataset and framework codes are publicly available to support further research.