Machine Learning Model To Detect Ddos Attack In Multi Uav Networks

The proliferation of Unmanned Aerial Vehicles (UAVs) in networked environments has introduced new security challenges, notably Distributed Denial of Service (DDoS) attacks. Existing machine learning models aimed at detecting such attacks often overlook the issue of misdiagnosis in classifying covert channels. Additionally, studies evaluating accident severity lack consideration for data heterogeneity and scale. To address these gaps, this research proposes an ensemble approach using decision trees, random forests, and logistic regression classifiers. By combining these models, the proposed system aims to enhance the accuracy and robustness of DDoS attack detection in multi-UAV networks. Through comprehensive classifier testing, the efficacy of the ensemble method in handling misclassification and accommodating diverse data characteristics is evaluated, contributing to more reliable security measures in UAV-based network environments.