Machine Learning Techniques to Detect a DDoS Attack in Flying AD-HOC Network

Flying Ad-hoc Network (FANET) consists of aerial devices, such as Unmanned Aerial Vehicles (UAVs), which work together to perform specific tasks. The system stands out because of its unique coverage, speed, and mobility capabilities. However, these features also make it vulnerable to various security threats, particularly in routing. One of the major threats to the availability of FANET is the Distributed Denial of Service (DDoS) flooding attack. These threats generate excessive traffic on network node, which causes frequent delays, packet loss, connectivity issues, and failure in operation. In this paper, we delve into detecting DDoS attacks by monitoring traffic patterns. We simulate a DDoS flooding attack scenario and explore different Machine Learning (ML) techniques to enhance detection accuracy.