Unmanned Aerial Vehicles (UAVs) have revolutionized industries such as defense, agriculture, and logistics due to their adaptability and ease of deployment. However, their growing dependence on wireless communication protocols, including MAVLink, UAVCAN, and UranusLink, introduces significant security challenges. This research offers a comprehensive security evaluation of the MAVLink protocol through experimental simulations in Software-In-The-Loop (SITL) environments. The study simulates Distributed Denial-of-Service (DDoS) attacks at both the Transmission Control Protocol (TCP) and User Datagram Protocol (UDP) layers to identify protocol vulnerabilities. Captured network traffic is compiled into a structured dataset and analyzed using machine learning algorithms, specifically Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN) algorithms, to differentiate between normal and malicious packets. The findings highlight critical security weaknesses in MAVLink communications and introduce a robust simulation and classification pipeline designed to enhance the effective detection of attacks, thereby improving UAV security.