Enhancing IIoT Security: BERT-Driven Intrusion Detection with MLP in Industrial Networks

Intrusion Detection Systems (IDS) are pivotal in securing Industrial Internet of Things (IIoT) networks, where the convergence of operational technology (OT) and information technology (IT) has heightened vulnerability to sophisticated cyber threats. The complexity, scale, and heterogeneity of IIoT environments necessitate advanced threat detection mechanisms capable of identifying and mitigating attacks in real-time. In this study, we propose a novel deep learning-based IDS framework that integrates Google BERT for advanced feature extraction and a Multi-Layer Perceptron (MLP) for robust classification. Our methodology is evaluated using three IIoT-specific benchmark datasets: CIC APT IIoT 2024, WUSTL IIoT 2021, and WUSTL IIoT 2018, which encompass diverse attack scenarios and network behaviors. To address the prevalent issue of class imbalance in these datasets, we employ the Synthetic Minority Over-sampling Technique (SMOTE), enhancing the model’s ability to learn and generalize minority attack patterns effectively. Experimental results demonstrate that our proposed framework significantly improves the detection accuracy of cyber threats in IIoT environments. The system’s scalability, efficiency, and real-time applicability make it a promising solution for safeguarding OT networks against evolving cyber threats. This study provides a practical and high-performance approach to enhancing the resilience of IIoT ecosystems.