Misleading Vehicles Detection System Using Hybrid Detection Model
AbstractOur understanding of road safety and efficiency has completely changed as a result of the introductiomn and evolution of autonomous vehicles (AVs) into transportation systems. AVs can organize and control the movements of the vehicles and react dynamically to traffic problems by utilizing the Internet of Vehicles (IoV) to make easier to identify the real-time communication between cars and infrastructure. They are vulnerable to cyberattacks, especially Distributed Denial of Service (DDoS) attacks, because they are connected to the networks in high degree. These assaults have the potential to seriously collapse the traffic,and interupt with communication, and decrease the safety.In order to meet the high demand for AVs to have a more flexible cybersecurity solution, this study presents the DDoS Attack Detection System (DADS) using hybrid detection model. A Hybrid Detection Model (HDM) serves as the foundation for DADS. To detect the complex attack patterns, the HDM uses a variety of classification machine learning techniques, including Random Forest, Adaboost, Naive Bayes, K-Nearest Neighbors (KNN), and decision trees. Together, these algorithms monitors the network traffic and differentiate between benign and malicious behavior.This increases the system’s performance and that is applicable in dynamic contexts by enabling it to recognize and react in real time to zero-day vulnerabilities and new DDoS attacks.The CIC-DDoS2019 dataset, a well-known benchmark for DDoS attack scenarios, and simulations carried out in SUMO (Simulation of Urban Mobility) were used to test the system. The results showed that DADS is a potential solution as it achieves high detection accuracy and offers a robust defense mechanism against both known and unknown DDoS threats in vehicle networks.