Blockchain-Integrated Hybrid Intrusion Detection System for IoT Networks | IJCT Volume 13 – Issue 2 | IJCT-V13I2P55
International Journal of Computer Techniques
ISSN 2394-2231
Author
Sandhya Jaiswal, Anurag Shrivastava
Abstract
The rapid proliferation of IoT devices has led to increased vulnerabilities in network infrastructures, making traditional centralized intrusion detection systems (IDS) insufficient to ensure security and data integrity. This study proposes an enhanced blockchain-based IDS framework that combines deep learning techniques with a decentralized ledger to detect and record network intrusions in IoT environments. The proposed system leverages a hybrid approach, integrating a Deep Neural Network (DNN) for accurate anomaly detection and a private blockchain for tamper-proof alert logging. Experimental results on a benchmark IoT intrusion dataset demonstrate significant improvements in detection accuracy, precision, and robustness against tampering. The framework ensures transparency, reliability, and resilience, providing a secure, real-time IDS solution suitable for modern IoT networks, and offering a scalable approach for future smart infrastructures.
Keywords
Blockchain, Intrusion Detection System, Internet of Things, Network Security, Machine Learning, Decentralization, Smart Contracts
Conclusion
This research study presented a hybrid CNN–LSTM-based intrusion detection framework designed for securing IoT networks against diverse cyber threats. By combining convolutional layers for automated feature extraction with LSTM networks for temporal dependency learning, the proposed model effectively captured complex traffic patterns. Experimental evaluation demonstrated superior performance compared to traditional machine learning and standalone deep learning models, achieving high accuracy and F1-score. The results confirm that hybrid deep learning architectures significantly enhance detection capability in imbalanced IoT datasets. Future work will focus on improving minority class detection, optimizing computational efficiency, and implementing the model in real-time IoT environments.
References
[1] S. R. Khonde et. al. “Hybrid intrusion detection system using
blockchain framework” Khonde and Ulagamuthalvi J Wireless Com Network (2022) 2022:58 https://doi.org/10.1186/s13638-022-02089-4 [2]Khawla Shalabi et. al “A Blockchain-based Intrusion Detection/Prevention” ScienceDirect, Procedia Computer Science 236 (2024) 410–419 [3] Shailendra Mishra et. al. “Blockchain and Machine Learning-Based Hybrid IDS to Protect Smart Networks and Preserve Privacy” https://doi.org/10.3390/ electronics12163524
[4] Khadija Begum et. al. “BFLIDS: Blockchain-Driven Federated Learning for Intrusion Detection in IoMT Networks” Blockchain-Driven Federated Learning for Intrusion Detection in IoMT Networks. Sensors 2024 https://doi.org/10.3390/ s24144591, MPDI 2024 [5] Jiachen Huang et. al. “Optimization Scheme of Collaborative Intrusion Detection System Based on Blockchain Technology” Electronics 2025, 14, 261 https://doi.org/10.3390/electronics14020261 [6] Atul Kumar1, et. al. “Secure blockchain based intrusion detection
for IoT networks” Kumar et al. Discover Computing (2025) 28:226, https://doi.org/10.1007/s10791-025-09754-4 Discover 2025 [7] Shailender Kumar Vats et. al. “Securing Distributed Blockchain Ledgers: An Intrusion Detection System Powered by Advanced Smart Contracts for Enhanced Cloud-Based Big Data Storage” International Journal of Intelligent Systems and Applications in Engineering IJISAE, 2024, 12(3), 901–909 [8] Chakir O, Sadqi Y, Abdellaoui Alaoui EA. An explainable machine learning-based web attack detection system for industrial
IoT web application security. Inform Secur J Glob Perspect. 2024; 1–27. [9] Awad M, Fraihat S, Salameh K, Redhaei A, A. Examining the suitability of netflow features in detecting IoT network intrusions.
Sensors. 2022;22(16):6164. [10] Swain PK, Pattnaik LM, Satpathy S. IoT applications and cyber threats: mitigation strategies for a secure future. In: Explainable
IoT applications: A demystification. Cham: Springer Nature Switzerland; 2025. p. 403–28. [11] Abed-alguni BH, Alzboun BM, Alawad NA. BOC-PDO: an intrusion detection model using binary opposition cellular prairie
dog optimization algorithm. Cluster Comput. 2024;27(10):14417–49. [12] Doriguzzi-Corin R, Knob LAD, Mendozzi L, Siracusa D, Savi M. Introducing packet-level analysis in programmable data
planes to advance network intrusion detection. Comput Networks. 2024;239:110162. [13] Batchu RK, Bikku T, Thota S, Seetha H, Ayoade AA. A novel optimization-driven deep learning model for the detection of
DDoS attacks. Sci Rep. 2024;14(1):28024. [14] Le TTH, Kim H, Kang H, Kim H. Classification and explanation for intrusion detection system based on ensemble trees and SHAP method. Sensors. 2022;22(3):1154. [15] Muna RK, Hossain MI, Alam MGR, Hassan MM, Ianni M, Fortino G. Demystifying machine learning models of massive IoT
attack detection with explainable AI for sustainable and secure future smart cities. Internet of Things. 2023;24:100919. [16] Fraihat S, Makhadmeh S, Awad M, Al-Betar MA, Al-Redhaei A. Intrusion detection system for large-scale IoT netflow networks
using machine learning with modified arithmetic optimization algorithm. Internet of Things. 2023;22:100819.
How to Cite This Paper
Sandhya Jaiswal, Anurag Shrivastava (2026). Blockchain-Integrated Hybrid Intrusion Detection System for IoT Networks. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
Related Posts:
