AutoML based Stacking Integration for Vehicle Network Anomaly Detection
Authors:
- 17 November 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 325-329
Abstract
Intelligent Connected Vehicle (ICV) is a new industrial form that deeply integrates industries such as automobiles, electronics, and information communication. However, abnormal in vehicle networks may lead to serious safety and performance issues. To improve the accuracy and efficiency of anomaly detection in vehicle networks, this paper proposes an Automated Machine Learning (AutoML) based on Stacking integration method. The proposed anomaly detection is implemented on the standard dataset, and the results show that our method has higher detection accuracy and robustness than the traditional single model. After automatic feature engineering, further select the most relevant features, reduce the calculation time, and significantly improve the model efficiency.Keywords
Funding Information
- National Natural Science Foundation of China
This publication has 10 references indexed in Scilit:
- Leveraging the Automated Machine Learning for Arabic Opinion Mining: A Preliminary Study on AutoML Tools and Comparison to Human Performance2022
- Dynamic Voting based Explainable Intrusion Detection System for In-vehicle Network2022
- Ensemble Learning Methods for Anomaly Intrusion Detection System in Smart Grid2021
- Whither AutoML? Understanding the Role of Automation in Machine Learning Workflows2021
- Machine Learning Techniques for IoT Data Analytics2021
- Automated Machine Learning: The New Wave of Machine Learning2020
- GIDS: GAN based Intrusion Detection System for In-Vehicle Network2018
- Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization2018
- Comparative Analysis of KNN Algorithm using Various Normalization TechniquesInternational Journal of Computer Network and Information Security, 2017
- Intrusion detection system based on the analysis of time intervals of CAN messages for in-vehicle network2016