Autonomous Vehicles (AVs) have revolutionized transportation by utilizing 6G technologies such as automated driving assistance, navigation, connected intelligence, and independent decision-making. Yet, the increasing reliance on AVs exposes the Internet of Vehicles (IoV) to potential vulnerabilities, making it susceptible to cyber attacks. One prominent threat is Distributed Denial of Service (DDoS) attacks, which can significantly impact AVs' safety and operational integrity. DDoS attacks directly disrupt the fundamental functionality of AVs to make timely and informed decisions, potentially leading to accidents or system failures. Despite the existence of numerous systems for detecting DDoS attacks, their continuous evolution in various attack patterns poses a significant challenge for effective detection. This paper provides a vision of 6G Security by proposing an Advanced DDoS Attack Detection System (ADADS) to enhance the detection capabilities of DDoS attacks by employing a Hybrid Detection Model (HDM) and a Continuous Learning Model (CLM) to adapt the evolving patterns of DDoS attacks over time dynamically. The collaborative integration of these models leverages the overall efficiency of DDoS attack detection, delivering a robust and adaptive defense mechanism. The experimental findings reveal that the proposed ADADS achieves a remarkable accuracy 98.7% with rapid stabilization in a few iterations for the current 6G specifications and applications.
Next-Gen Security: Enhanced DDoS Attack Detection for Autonomous Vehicles in 6G Networks
2024-06-24
1029739 byte
Conference paper
Electronic Resource
English
Security enhanced planning system with anomaly detection for autonomous vehicles
European Patent Office | 2023
|Attack Models and Countermeasures for Autonomous Vehicles
Springer Verlag | 2021
|SAE Technical Papers | 2020
|