Abstract

Wireless sensor networks (WSNs) are thought to be the foundation of the Internet of Things (IoT), as the majority of IoT devices are constructed using wireless sensor node technology. Denial-of-service (DoS) attacks are one of the many security risks to which WSNs are susceptible. These attacks have the potential to seriously impair the network's operation and performance. The accuracy and effectiveness of traditional approaches for identifying DoS assaults in WSNs are frequently lacking. The aim of this study is to develop a machine learning-based model for precisely and instantly detecting DoS assaults in WSNs. The suggested approach makes use of machine learning techniques to examine network traffic patterns and spot malicious activity linked to denial-of-service assaults. Two layers of enhancement were employed to enhance the proposed model, developing a balanced dataset and utilizing an appropriate feature selection technique. The proposed classifier which is based on Decision Tree (DT) classification model, has achieved high prediction accuracy with minimum overhead compared to existing detection methods. It achieved classification accuracies that reached 100%, 99.4%, 98.6%, and 99.4% for detecting flooding, blackhole, scheduling, and grayhole attacks, respectively. It has been compared to several recent existing techniques and shows better performance It is noteworthy that the proposed classification model can significantly meet WSN limitations and constraints because it is based on a lightweight classifier with a feature selection method that greatly decreases computational overhead. In conclusion, this research article offers two main contributions: it introduces an effective model for detecting DoS assaults and develops a balanced dataset (ROS-WSN-DS) using a random oversampling technique, which significantly improves classification accuracy and performance. The developed balanced dataset, ROS-WSN-DS, significantly improved the classification accuracy and performance compared to the original dataset, WSD-DS