Machine Learning Model To Detect Ddos Attack In Multi Uav Networks

Project Code :TCMAPY1690

Objective

The primary objective of this project is to develop a robust and accurate machine learning-based system for detecting Distributed Denial of Service (DDoS) attacks in multi-UAV (Unmanned Aerial Vehicle) network environments. With the growing integration of UAVs in critical communication and operational networks, ensuring their security has become paramount. Traditional detection methods often fall short in identifying covert attack patterns and managing the complex, heterogeneous nature of UAV-generated data. This research addresses these challenges by proposing an ensemble approach that leverages the strengths of Decision Trees, Random Forests, and Logistic Regression classifiers.

Abstract

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.

Keywords: UAVs, DDoS, Security Challenges, Machine Learning, Ensemble algorithms, Random Forest, Decision Tree and Logistic Regression.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.