Publication Type : Conference Paper
Publisher : IEEE
Source : 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC)
Url : https://doi.org/10.1109/icesc60852.2024.10690016
Campus : Chennai
School : School of Computing
Department : Computer Science and Engineering
Year : 2024
Abstract :
Autonomous vehicles (AVs) are susceptible to cyberattacks due to their reliance on vehicle-to-everything (V2X) communication. This research proposes a Gradient Boosting-based intrusion detection system to safeguard AV networks. By employing advanced machine learning techniques, including Adaboost, Decision Trees, and Random Forests, the system effectively identifies various cyberattacks. Evaluated on standard datasets, the proposed IDS achieves a remarkable accuracy of 99.49%, surpassing existing models. The combination of feature selection and ensemble learning enhances the system's detection rate while maintaining computational efficiency.
Cite this Research Publication : Siva Gayatri Venkata Naga, Datta Sai Ammanamanchi, Angela Raj Chadha, Kethamreddy Karthikeya Reddy, Udhaya Kumar Shanmugam, A Boosting-Based Machine Learning Approach for Intrusion Detection in Vehicle Address Verification Systems, 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC), IEEE, 2024, https://doi.org/10.1109/icesc60852.2024.10690016