Enhancing IoT Security: Machine Learning-Based Network Intrusion Detection

The Internet of Things(IoT) can enhance lives in various ways by facilitating more interaction, technology, and decision-making based on data. The use of IoT devices is growing, which has increased the risk of network intrusion and other security concerns. This paper suggests a machine learning(ML)-based approach for IoT systems' network intrusion detection(NID). The model has been evaluated using a NID dataset that is openly accessible. The strategy uses a variety of ML methods including Naive Bayes(NB), K-Nearest Neighbour(KNN), Decision Tree(DT) and Logistic Regression(LR) for data preprocessing, feature selection, and model selection. The performance of these models has been analyzed using metrics like accuracy, recall, precision and F1-score. The results demonstrate that the utilized method can successfully identify network threats and enhance the resources of IoT systems. The results of this study may be helpful to academics and professionals working on the subject of IoT security. In comparison with NB, DT and KNN, which had accuracy rates of 90.68%, 99.16% and 95.55%, respectively, the system found that DT had the best accuracy, with a rate of 99.47%.