A Blockchain-Enabled Machine Learning Intrusion Detection System to Protect Internet of Things
Open Access DepositedThe Internet of Things (IoT) revolutionizes our technological landscape by transforming everyday devices into a global network of internet-connected sensors across consumer, commercial, and industrial domains. However, this widespread adoption of IoT devices also expands the attack surface for cyber threats. To mitigate these risks, this study proposes a blockchain-enabled machine learning approach for securing IoT networks.The study evaluates seven standard machine learning models: Gaussian Naive Bayes (GNB), Decision Tree (DT), Random Forest (RF), Linear Support Vector Machine (LSVM), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), and Multi-Layer Perceptron (MLP). Among these models, XGBoost emerges as the most effective algorithm for intrusion detection on IoT networks. In addition, the study demonstrates the potential of Ethereum Smart Contracts within a decentralized network to enhance security while maintaining device integrity. The practical implications of this study are significant for both industry practitioners and researchers. For practitioners, integrating XGBoost with blockchain technology offers a robust solution to detect and mitigate cyber threats, thereby mitigating the risk of IoT malware attacks and ensuring the smooth operation of IoT devices. For researchers, this study provides a practical framework for further exploration of machine learning and blockchain integration, thereby encouraging the development of more advanced security solutions for IoT environments. In conclusion, the integration of machine learning with blockchain technology offers a promising solution for securing IoT networks. XGBoost, in particular, emerges as a powerful tool for intrusion detection. By leveraging smart contracts, we can further enhance security while maintaining the integrity of IoT devices.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.