Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{185893,
        author = {Aniruddha Jaipurkar},
        title = {Adaptive Intrusion Detection System for Controller Area Network (CAN) in Automotive Cybersecurity},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {4182-4187},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185893},
        abstract = {The increasing complexity of automotive technology has led to the need for more effective ways to secure the communication between vehicles' controllers. This research paper presents an adaptive Intrusion Detection System (IDS) designed to protect the integrity of Controller Area Network (CAN) networks in modern vehicles. The study evaluates the performance of various machine learning and deep learning algorithms within the IDS framework. The goal is to understand the unique security challenges of CAN networks and develop effective intrusion detection measures. The research methodology involves collecting a representative dataset of CAN network traffic and extracting meaningful features using statistical, time-domain, and frequency-domain analysis. The dataset is then transformed into images for enhanced analysis and visualization. The comparative analysis of machine learning algorithms demonstrates that the CNN+GRU and DL-CNN models outperform others in terms of accuracy and robustness in detecting unauthorized access. These deep learning models excel at capturing complex temporal and pattern dependencies, critical for identifying abnormal activities in CAN networks. The findings contribute to the development of an adaptive IDS specifically tailored for CAN networks, addressing the security concerns of modern automotive systems. The utilization of image-based analysis techniques provides valuable insights into traffic patterns, aiding in effective intrusion detection. By leveraging machine learning algorithms, particularly the CNN+GRU and DL-CNN models, the IDS demonstrates improved performance in terms of accuracy and robustness. The research outcomes pave the way for advanced IDS development, enhancing the overall security of automotive systems.},
        keywords = {Intrusion detection system, In-vehicle, CAN, CNN, GRU.},
        month = {November},
        }