A LIGHTWEIGHT MACHINE LEARNING APPROACH FOR DENIAL-OF-SERVICE ATTACKS DETECTION IN WIRELESS SENSOR NETWORKS

            Wireless Sensor Networks are widely used in various real-world applications, but their limited resources and open communication environment make them highly vulnerable to security threats such as Denial-of-Service attacks. These attacks can significantly disrupt network performance by exhausting the energy and computational resources of sensor nodes. Therefore, efficient and lightweight detection mechanisms are essential to maintain the reliability and availability of WSN systems.   In this study, a lightweight machine learning approach was proposed to detect DoS attacks in        Wireless Sensor Networks. Several machine learning algorithms, including Decision Tree, Logistic Regression, Naïve Bayes, and Random Forest, were analyzed to identify the most suitable method for resource-constrained environments. The experimental results indicate that Decision Tree and Random Forest algorithms provide a good balance between detection accuracy, computational efficiency, and processing speed. The proposed approach effectively distinguishes between normal and malicious network traffic while maintaining low computational overhead.           Overall, the study demonstrates that lightweight machine learning techniques can significantly improve the security of wireless sensor networks without imposing heavy resource requirements. The proposed model can help enhance the reliability, efficiency, and security of WSN-based systems deployed in critical applications.  

[1] G. Al Sukkar and S. Al-Sharaeh, “Enhancing security in wireless sensor networks: A machine learning-based DoS attack detection,” Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19712–19719, 2025.   [2] B. Kaur, D. Prashar, and L. Mrsic, “Enhancing the reliability and accuracy of wireless sensor networks using a deep learning and blockchain approach with DV-HOP algorithm for DDoS mitigation,” Journal on Wireless Communications and Networking, vol. 2025, pp. 1–18, 2025.   [3] S. Joo, S. Park, H. Shim, Y. Oh, and I. Lee, “Machine learning-based detection and selective mitigation of denial-of-service attacks in wireless sensor networks,” Computers, Materials & Continua, vol. 82, no. 2, pp. 2475–2494, 2025.   [4] A. Sharma and S. Rani, “An optimized ensemble approach for securing wireless sensor networks against attacks,” ICCK Transactions on Wireless Networks, vol. 1, no. 1, pp. 5–15, 2025.   [5] T. Thanigaivel, S. Venkatesh, M. Monish, and T. Gobinath, “A machine learning-driven framework for DoS attack detection in cluster-based wireless sensor networks,” International Research Journal of Modernization in Engineering Technology and Science, vol. 7, no. 3, pp. 1–8, 2025.   [6] H. Barati, “A quantum genetic algorithm-enhanced self-supervised intrusion detection system for wireless sensor networks in IoT,” arXiv preprint, 2025.   [7] M. M. Alhusseini and M. R. F. Derakhshi, “Hybrid AI-driven intrusion detection framework leveraging feature selection for enhanced network security,” arXiv preprint, 2025.   [8] C. Panggabean, C. Venkatachalam, P. Shah, S. John, R. Devi, and S. Venkatachalam, “Intelligent DoS and DDoS detection using hybrid GRU-NTM deep learning model,” arXiv preprint, 2025.   [9] M.-L. A. Bartsioka, I. A. Bartsiokas, P. K. Gkonis, D. I. Kaklamani, and I. S. Venieris, “Machine learning enabled eavesdropper detection in beyond-5G IIoT networks,” arXiv preprint, 2025.   [10] D. Sethi, M. Gora, S. Jain, S. Kumari, S. Gupta, and T. Tyagi, “Implementing wireless sensor networks through machine learning techniques,” Recent Patents on Engineering, vol. 15, no. 3, pp. 268–280, 2025.