Lightweight Machine Learning-Based DOS Attack Detection in Wireless Sensor Networks Using Decision Tree and Information Gain

Wireless Sensor Networks (WSNs) are rapidly expanding across various domains due to their unique characteristics and performance capabilities. However, these networks are highly vulnerable to a range of security threats, particularly Denial-of-Service (DoS) attacks, which are among the most common in WSNs. This paper explores the vulnerabilities of WSNs, focusing on DoS threats, and reviews current techniques for their detection. It introduces a lightweight machine learning-based approach using a decision tree (DT) algorithm with the Information Gain (IG) feature selection method for efficient DoS detection. Tested on an enhanced WSN-DS dataset, the proposed method demonstrated high accuracy and minimal processing time compared to other classifiers, such as XGBoost, and RF. This efficiency makes the proposed method well-suited for real-time DoS attack detection in resource-constrained WSNs.