Denial of service detection using dynamic time warping

With the rapid growth of security threats in computer networks, need for developing efficient security-warning systems is substantially increasing. Distributed denial-of-service (DDoS) and DoS attacks are still among most effective dreadful that require robust detection. In this work, we propose a new method to detect TCP DoS/DDoS attacks. Since analyzing network traffic promising approach, our proposed utilizes by decomposing into control data planes exploiting dynamic time warping (DTW) algorithm aligning these two with respect minimum Euclidean distance. By demonstrating distance between considerably small benign traffic, exploit characteristic detecting as outliers. An adaptive thresholding scheme implemented adjusting value threshold accordance local statistics median absolute deviation (MAD) distances planes. We demonstrate efficacy obtained from publicly available datasets.