Detection of DoS Attacks in WSNs by using Machine Learning Models

Wireless Sensor Networks (WSNs) are crucial in modern communication systems, characterized by their deployment of spatially distributed sensor nodes to monitor and collect data from the environment. These networks, often used in critical applications such as environmental monitoring, healthcare, and military surveillance, are increasingly vulnerable to Denial of Service (DoS) attacks. A DoS attack aims to disrupt the normal operation of a network by overwhelming its resources, thereby denying legitimate users access to the services provided by the network. Given the sensitivity and critical nature of the data handled by WSNs, ensuring their security is of paramount importance. Machine learning has emerged as a powerful tool in improving the security of WSNs by enabling the detection of anomalous patterns that may indicate the presence of a DoS attack. This study focuses on using machine learning models to detect DoS attacks in WSNs, an essential step in protecting these networks. In this paper, several machine learning models were employed to identify DoS attacks, including Logistic Regression, Support Vector Machine, Naive Bayes, Decision Tree, Random Forest, K-nearest Neighbor, and XGBoost. The performance of these models was rigorously evaluated to determine their effectiveness in accurately detecting and mitigating the impact of DoS attacks on WSNs. The findings underscore the importance of integrating machine learning techniques into WSN security frameworks, offering a robust solution to the growing threat of DoS attacks.