A Blockchain-Assisted Hybrid Deep Learning Framework for Intrusion Detection in Industrial Internet of Things Networks
DOI:
https://doi.org/10.65204/djes.v3i2.799Keywords:
Industrial Internet of Things , Intrusion Detection System , Blockchain Security, Deep Learning, Network SecurityAbstract
This enables millions of connected devices and smart manufacturing systems, making IIoT an integral part of Industry 4.0 environments. Nonetheless, the fast growth of IIoT infrastructures has tremendously augmented industrial network exposure to various cyber attacks like DDoS, scanning and infiltration. Existing intrusion detection systems have difficulty managing and reliability reporting of threats in scalable distributed environments. To counter these challenges, this paper presents a novel vertical hybrid intrusion detection framework assisted by the blockchain to integrate a deep learning-based model for detection with blockchains in decentralized infrastructure. This paper proposes a system that leverages the Bidirectional Long Short-Term Memory (BiLSTM) network model to learn about temporal traffic patterns in the time series for IIoT network flows. Using Blockchain technology, we secure the IDS logs for integrity and transparency of threat data shared between distributed nodes. The proposed approach is evaluated using experiments on the BOT-IoT dataset, where it achieves a 99.3% detection accuracy and surpasses many state-of-the-art models for intrusion detection. Results Demonstrate the potential improvement of IIoT intrusion detection systems with integrated blockchain and deep learning methods.
References
Khraisat, A., Gondal, I., Vamplew, P., and Kamruzzaman, J., 2019, Survey of intrusion detection systems: Techniques, datasets and challenges, Cybersecurity, 2(1), pp. 1–22.
Moustafa, N., and Slay, J., 2015, The UNSW-NB15 dataset for network intrusion detection systems, Proc. Military Communications and Information Systems Conference, Canberra, Australia.
Yang, R., Zhang, Y., and Liu, Y., 2023, Efficient intrusion detection toward IoT networks using cloud–edge collaborative learning, Computer Networks, 222, p. 109529.
Alsudani, S. W. A., and Ghazikhani, A., 2023, Enhancing intrusion detection with LSTM recurrent neural network optimized by emperor penguin algorithm, WJCMS, 2(3), pp. 69–80.
Yaras, S., Aydin, H., and Aydin, M., 2024, IoT-based intrusion detection system using deep learning methods in big data environments, Electronics, 13(6), p. 1053.
Nazir, A., Khan, A., and Rizwan, M., 2024, Hybrid CNN-LSTM architecture for accurate IoT threat detection, ICT Express, 10(3), pp. 512–520.
Alsudani, S. W. A., Feizi-Derakhshi, M.-R., Mutasher, W. G., Nasrawi, H. A. M., and Aswad, M. A., 2025, Enhancing IoT intrusion detection through a hybrid deep learning model with dragonfly-based feature and ensemble optimization, International Journal of Communication Networks and Information Security, 17(5), pp. 1–15.
Xi, C., Li, H., and Zhang, Y., 2024, IDS-MTran: A multi-scale transformer model for network intrusion detection, Scientific Reports, 14, p. 74214.
Zhang, C., Wang, Y., and Li, H., 2025, Hybrid CNN-BiLSTM-Transformer intrusion detection model for IoT networks, Sensors, 25(9), p. 2725.
Sadhwani, S., and Kumar, R., 2025, Hybrid BiLSTM-CNN model for intrusion detection in IoT environments, Scientific Reports, 15.
Alsudani, S., Nasrawi, H., Shattawi, M., and Ghazikhani, A., 2024, Enhancing spam detection: A crow-optimized FFNN with LSTM for email security, WJCMS, 3(1), pp. 28–39.
Bamber, S., Singh, P., and Sharma, R., 2025, Hybrid CNN-LSTM approach for intelligent cyber intrusion detection, Computers & Security, 137.
Sinha, P., Kumar, A., and Gupta, R., 2025, High-performance LSTM-CNN secure architecture for IoT intrusion detection, IEEE Access, 13, pp. 24560–24575.
Alsharif, N. A., Alharbi, A., and Alqahtani, S., 2023, Intrusion detection system for IoT using machine learning and blockchain technology, Engineering, Technology & Applied Science Research, 13(2), pp. 10524–10531.
Ravuri, A., and Kumar, R., 2024, Blockchain-enabled collaborative anomaly detection for IoT security, MATEC Web of Conferences, 403.
Abou El Houda, Z., Hafid, M., and Khoukhi, L., 2024, Blockchain-enabled federated learning for secure intrusion detection in edge-enabled IoT networks, IEEE Transactions on Intelligent Transportation Systems, 25(3), pp. 3012–3023.
Shalabi, K., and Al-Omari, H., 2024, Blockchain-based intrusion detection and prevention systems for IoT networks: A systematic review, Procedia Computer Science, 234, pp. 85–94.
Alsudani, S., and Saeea, M. N., 2023, Enhancing thyroid disease diagnosis through emperor penguin optimization algorithm, WJPS, 2(4), pp. 66–79.
Song, W., Zhu, X., Ren, S., Tan, W., and Peng, Y., 2025, A hybrid blockchain and machine learning approach for intrusion detection system in industrial Internet of Things, Alexandria Engineering Journal, 127, pp. 619–627.
Kumar, A., and Singh, P., 2025, Secure blockchain-based intrusion detection for IoT networks, Journal of Network and Systems Management, 33(2).
Qawasmeh, S., and Al-Fayoumi, M., 2025, Hybrid CNN-based intrusion detection framework for IoT networks, Tikrit Journal of Engineering Sciences, 32(1), pp. 50–60.
Kaissar, A., Nassif, A. B., Soudan, B., and Injadat, M., 2025, Enhancing CNN-based network intrusion detection through hyperparameter optimization, Intelligent Systems with Applications, 26, p. 200528.
Agarwal, S., and Mehra, P. S., 2025, Evaluating LSTM and Bi-LSTM for binary classification in intrusion detection system in IoT, AIP Conference Proceedings, 3325(1), p. 070008.
Alemayehu, M., Ghanem, M. C., Kheddar, H., Dunsin, D., Kerrache, C. A., and Rathee, G., 2026, Real-time DDoS detection in industrial IoT using proximal policy optimisation and deep reinforcement learning, Preprints.
Ashraf, J., Raza, G. M., Kim, B.-S., Wahid, A., and Kim, H.-Y., 2025, Making a real-time IoT network intrusion-detection system using a realistic BoT–IoT dataset with multiple machine-learning classifiers, Applied Sciences, 15(4), p. 2043.
Hakami, H., Faheem, M., and Ahmad, M. B., 2025, Machine learning techniques for enhanced intrusion detection in IoT security, IEEE Access, 13, pp. 31140–31158.
U, N., and Kumar, S. V. N. S., 2025, An enhanced whale optimizer based feature selection technique with effective ensemble classifier for network intrusion detection system, Peer-to-Peer Networking and Applications, 18.
Zhang, C., Li, J., Wang, N., and Zhang, D., 2025, Research on intrusion detection method based on transformer and CNN-BiLSTM in Internet of Things, Sensors, 25(9), p. 2725.
Alsudani, S. W. A., and Saud, G. K., 2025, Recurrent neural network optimized by grasshopper for accurate audio data-based diagnosis of Parkinson’s disease, WJPS, 4(2), pp. 56–75.
Latif, N., Ma, W., and Ahmad, H. B., 2025, Advancements in securing federated learning with IDS: A comprehensive review of neural networks and feature engineering techniques for malicious client detection, Artificial Intelligence Review, 58, p. 91.
H. Nandanwar and R. Katarya, “A hybrid blockchain-based framework for securing intrusion detection systems in Internet of Things,” Cluster Computing, vol. 28, p. 471, 2025, doi: 10.1007/s10586-025-05135-0.
F. F. Alruwaili, “Blockchain-powered deep learning for Internet of Things with cloud-assisted secure smart home networks,” IEEE Access, vol. 12, pp. 119927–119936, 2024, doi: 10.1109/ACCESS.2024.3450796.
A. Govindaram and J. A., “FLBC-IDS: A federated learning and blockchain-based intrusion detection system for secure IoT environments,” Multimedia Tools and Applications, vol. 84, pp. 17229–17251, 2025, doi: 10.1007/s11042-024-19777-6.
