Advanced Search
Turn off MathJax
Article Contents
WANG Kai, LIU Hengyang, WANG Bailing. RepCAN: A Lightweight Intrusion Detection Method for In-Vehicle Networks Integrating Temporal Graph Re-parameterization[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260403
Citation: WANG Kai, LIU Hengyang, WANG Bailing. RepCAN: A Lightweight Intrusion Detection Method for In-Vehicle Networks Integrating Temporal Graph Re-parameterization[J]. Journal of Electronics & Information Technology. doi: 10.11999/JEIT260403

RepCAN: A Lightweight Intrusion Detection Method for In-Vehicle Networks Integrating Temporal Graph Re-parameterization

doi: 10.11999/JEIT260403 cstr: 32379.14.JEIT260403
Funds:  The National Natural Science Foundation of China(62272129), Taishan Scholar Foundation of Shandong Province, China (tsqn202408112)
  • Received Date: 2026-04-07
  • Accepted Date: 2026-09-17
  • Rev Recd Date: 2026-09-17
  • Available Online: 2026-09-24
  •   Objective  With the rapid adoption of Intelligent Connected Vehicles (ICVs), interactions between the previously isolated In-Vehicle Network (IVN) and external systems are becoming increasingly frequent, exposing vehicles to cyberattacks such as message injection and semantic manipulation. Remote compromise can result in core control system hijacking, sensitive data leakage, and fatal accidents. Intrusion detection systems are widely used in academia and industry because they are protocol-independent and can be deployed non-intrusively. Furthermore, the R155 regulation issued by the UN/WP.29 requires vehicles placed on the market to have IVN intrusion detection capabilities. Although deep learning models have become a mainstream approach to IVN intrusion detection because of their strong feature extraction capabilities, deep Graph Neural Networks (GNNs) and large transformer models impose substantial computational and memory demands on in-vehicle edge devices. To address these challenges, this study proposes RepCAN, a lightweight intrusion detection method for IVNs that integrates temporal graph re-parameterization. The method targets the Controller Area Network (CAN) protocol within a vehicle-cloud collaborative architecture and combines a “ghost node” mechanism with lossless architectural transformations to balance detection generalization and low resource consumption.  Methods  The proposed RepCAN framework is designed for real-world automotive environments and comprises three core modules. First, a graph construction and data augmentation module converts the unstructured raw CAN message stream into semantic tensors that can be processed by GNNs. A hierarchical sliding-window strategy extracts two complementary feature groups within each window: statistical features and physical-domain features derived from the CAN payload. Statistical features include message entropy, average message period, and period jitter, which capture fuzzing noise and timing anomalies. For physical-domain features, first-order differences in payload values are calculated to detect discontinuities, and discrete wavelet transforms are used to extract the energy spectrum of the detail coefficients. These features support the detection of attacks that mimic normal traffic without explicit semantic decoding. For graph construction, a dual-stream graph architecture and a “ghost node” mechanism are introduced. A learnable global static adjacency matrix encodes prior information about the physical topology and control logic, whereas a dynamic adjacency matrix is generated adaptively from communication frequencies and inter-message intervals. The ghost node redirects sudden out-of-distribution messages to a virtual node, allowing anomalous traffic to be represented through changes in node features and dynamic edges. Second, a spatiotemporal feature extraction module uses a multi-branch Re-parameterized Graph Convolutional Network (RepGCN) and a Re-parameterized Temporal Convolutional Network (RepTCN) during training to capture complex spatiotemporal dependencies. RepGCN models spatial dependencies through multi-head aggregation, capturing relationships among Electronic Control Units (ECUs) across different feature subspaces. RepTCN uses multi-branch temporal convolutions with different kernel sizes to capture multiscale short- and long-term temporal patterns. During inference, structural re-parameterization mathematically collapses these multi-branch architectures into efficient single-path structures. Third, an unsupervised anomaly detection module uses Deep Support Vector Data Description (Deep SVDD) to map the extracted spatiotemporal features into a minimum enclosing hypersphere. Anomalies are detected without labels by calculating the Euclidean distance between each test sample and the hypersphere center.  Results and Discussions  Extensive experiments are conducted on the Car-Hacking dataset, which contains normal traffic and four attack types: Denial of Service (DoS), Fuzzy, Gear, and Revolutions Per Minute (RPM) (Table 1). Comparisons with representative supervised and unsupervised baseline methods demonstrate the effectiveness of RepCAN. In the unsupervised setting, RepCAN achieves an accuracy of 0.984 0, an F1 score of 0.979 8, and an Area Under the Curve (AUC) of 0.994 2, outperforming all unsupervised baselines and achieving performance comparable to or better than several supervised models (Table 2). RepCAN also achieves a False Positive Rate (FPR) of 0.011 7 and a recall of 0.977 4, demonstrating its ability to balance missed detections and false alarms in highly imbalanced vehicular network scenarios. Feature ablation experiments show that combining statistical and physical-domain features improves detection performance and robustness, yielding an F1 score of 0.979 8, compared with 0.952 1 for statistical features alone and 0.939 9 for physical-domain features alone (Table 3). Topological ablation experiments further show that removing the ghost node mechanism reduces the F1 score to 0.890 2, demonstrating its contribution to the adaptive detection of unknown threats. Removing the dual-stream structure or the multi-branch re-parameterization module also degrades overall performance (Table 4). To evaluate practical deployment feasibility, the framework is tested in a vehicle-cloud collaborative environment using an NVIDIA Jetson Orin Nano edge computing device (Fig. 2). Structural re-parameterization reduces the model’s parameter count by 64.15% and the number of Floating-Point Operations (FLOPs) by 59.32% during inference (Table 5). RepCAN achieves an overall inference latency of 0.004 827 ms per message on the in-vehicle device (Fig. 3), substantially below the shortest physical transmission time of a CAN message (approximately 0.1–0.15 ms). This low latency supports real-time operation and reduces the potential for competition for computing resources with core driving tasks. RepCAN’s runtime memory use is approximately 360 MB, substantially lower than that of many baseline models, supporting its suitability for resource-constrained in-vehicle devices (Fig. 4). Evaluation on the full Car-Hacking test set of 662 741 samples (Table 6) supports the numerical consistency of the re-parameterization mechanism: mean absolute errors in deep features are on the order of 10-4, and ΔAUC remains below 0.000 7 across all attack types. Additional evaluation of masquerade attacks in the ROAD dataset reveals substantial performance degradation, with an overall accuracy of 0.523 7, an AUC of 0.768 0, and an F1 score of 0.001 5 (Table 7). These results indicate that attacks preserving normal timing patterns remain difficult to detect with the current framework.  Conclusions  This study proposes RepCAN, a lightweight CAN-bus intrusion detection method that integrates temporal graph re-parameterization. Its ghost node mechanism maps out-of-distribution anomalous traffic to a virtual node, improving structural representation and model generalization without expanding the graph scale. Structural re-parameterization also reconciles the need for high-capacity, multiscale training with low-latency inference. Evaluations on the benchmark dataset and hardware platform demonstrate that RepCAN achieves a strong balance between detection performance and low resource consumption. Future work will focus on stealthy masquerade attacks by incorporating fine-grained semantic analysis to address the current limitations in detecting attacks that preserve normal timing patterns.
  • loading
  • [1]
    韩乔妮, 马建国, 李鹏, 等. 混合网络攻击下车辆队列的无模型自适应弹性控制[J]. 电子与信息学报, 2026, 48(5): 2066–2076. doi: 10.11999/JEIT251135.

    HAN Qiaoni, MA Jianguo, LI Peng, et al. Model-free adaptive resilient control of vehicle platoons against hybrid cyberattacks[J]. Journal of Electronics & Information Technology, 2026, 48(5): 2066–2076. doi: 10.11999/JEIT251135.
    [2]
    WANG Kai, ZHANG Aiheng, SUN Haoran, et al. Analysis of recent deep-learning-based intrusion detection methods for in-vehicle network[J]. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(2): 1843–1854. doi: 10.1109/TITS.2022.3222486.
    [3]
    YING Xuhang, SAGONG S U, CLARK A, et al. Shape of the cloak: Formal analysis of clock skew-based intrusion detection system in controller area networks[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(9): 2300–2314. doi: 10.1109/TIFS.2019.2895957.
    [4]
    MÜTER M and ASAJ N. Entropy-based anomaly detection for in-vehicle networks[C]. 2011 IEEE Intelligent Vehicles Symposium (IV), Baden-Baden, Germany, 2011: 1110–1115. doi: 10.1109/IVS.2011.5940552.
    [5]
    CHO K T and SHIN K G. Fingerprinting electronic control units for vehicle intrusion detection[C]. The 25th USENIX Conference on Security Symposium, Austin, USA, 2016: 911–927.
    [6]
    GROZA B and MURVAY P S. Efficient intrusion detection with bloom filtering in controller area networks[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(4): 1037–1051. doi: 10.1109/TIFS.2018.2869351.
    [7]
    张瑞丰, 杨荣妮. 拒绝服务攻击下信息物理系统的数据驱动安全控制: 一种在线模态依赖的切换-Q-学习策略[J]. 电子与信息学报, 2026, 48(4): 1424–1433. doi: 10.11999/JEIT250746.

    ZHANG Ruifeng and YANG Rongni. Data-driven secure control for cyber-physical systems under denial-of-service attacks: An online mode-dependent switching-Q-learning algorithm[J]. Journal of Electronics & Information Technology, 2026, 48(4): 1424–1433. doi: 10.11999/JEIT250746.
    [8]
    XIE Guoqi, YANG L T, YANG Yuanda, et al. Threat analysis for automotive CAN networks: A GAN model-based intrusion detection technique[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(7): 4467–4477. doi: 10.1109/TITS.2021.3055351.
    [9]
    MCHERGUI A, MOULAHI T, and ZEADALLY S. Survey on artificial intelligence (AI) techniques for vehicular ad-hoc networks (VANETs)[J]. Vehicular Communications, 2022, 34: 100403. doi: 10.1016/j.vehcom.2021.100403.
    [10]
    RAJAPAKSHA S, KALUTARAGE H, AL-KADRI M O, et al. AI-based intrusion detection systems for in-vehicle networks: A survey[J]. ACM Computing Surveys, 2023, 55(11): 237. doi: 10.1145/3570954.
    [11]
    LAMPE B and MENG Weizhi. A survey of deep learning-based intrusion detection in automotive applications[J]. Expert Systems with Applications, 2023, 221: 119771. doi: 10.1016/j.eswa.2023.119771.
    [12]
    AL-AQL N and AL-SHAMMARI A. Hybrid RNN-LSTM networks for enhanced intrusion detection in vehicle CAN systems[J]. Journal of Electrical Systems, 2024, 20(6s): 3019–3031. doi: 10.52783/jes.3318.
    [13]
    XU He, WU Di, LU Yufeng, et al. Models on the move: Towards feasible embedded AI for intrusion detection on vehicular CAN bus[C]. The 2024 USENIX Conference on Usenix Annual Technical Conference, Santa Clara, USA, 2024: 64.
    [14]
    HOSSAIN M D, INOUE H, OCHIAI H, et al. An effective in-vehicle CAN bus intrusion detection system using CNN deep learning approach[C]. GLOBECOM 2020-2020 IEEE Global Communications Conference, Taipei, China, 2020: 1–6. doi: 10.1109/GLOBECOM42002.2020.9322395.
    [15]
    JAVED A R, UR REHMAN S, KHAN M U, et al. CANintelliIDS: Detecting in-vehicle intrusion attacks on a controller area network using CNN and attention-based GRU[J]. IEEE Transactions on Network Science and Engineering, 2021, 8(2): 1456–1466. doi: 10.1109/TNSE.2021.3059881.
    [16]
    ZHANG Hengrun, ZENG Kai, and LIN Shuai. Federated graph neural network for fast anomaly detection in controller area networks[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 1566–1579. doi: 10.1109/TIFS.2023.3240291.
    [17]
    HE Yaru, GAO Jiaqi, FAN Mingrui, et al. A&D graph-based graph neural network intrusion detection for in-vehicle controller area network[C]. 2024 IEEE/CIC International Conference on Communications in China (ICCC), Hangzhou, China, 2024: 1281–1286. doi: 10.1109/ICCC62479.2024.10681772.
    [18]
    ALKHATIB N, MUSHTAQ M, GHAUCH H, et al. CAN-BERT do it? Controller area network intrusion detection system based on BERT language model[C]. 2022 IEEE/ACS 19th International Conference on Computer Systems and Applications (AICCSA), Abu Dhabi, United Arab Emirates, 2022: 1–8. doi: 10.1109/AICCSA56895.2022.10017800.
    [19]
    WU Zhongqiang and LI Mengting. ResNet-Swin Transformer based intrusion detection system for in-vehicle network[J]. Expert Systems with Applications, 2025, 279: 127547. doi: 10.1016/j.eswa.2025.127547.
    [20]
    谈名名, 张恒, 王鑫, 等. 一种融合时序与深度特征的二阶段CAN总线攻击识别方法[J]. 电子与信息学报, 2026, 48(4): 1444–1453. doi: 10.11999/JEIT250651.

    TAN Mingming, ZHANG Heng, WANG Xin, et al. A two-stage framework for CAN bus attack detection by fusing temporal and deep features[J]. Journal of Electronics & Information Technology, 2026, 48(4): 1444–1453. doi: 10.11999/JEIT250651.
    [21]
    WANG Yingqing, QIN Guihe, ZOU Mi, et al. A lightweight intrusion detection system for internet of vehicles based on transfer learning and MobileNetV2 with hyper-parameter optimization[J]. Multimedia Tools and Applications, 2024, 83(8): 22347–22369. doi: 10.1007/s11042-023-15771-6.
    [22]
    WANG Shaoqiang, WANG Yizhe, ZHENG Baosen, et al. Intrusion detection system for vehicular networks based on MobileNetV3[J]. IEEE Access, 2024, 12: 106285–106302. doi: 10.1109/ACCESS.2024.3437416.
    [23]
    JEONG S, LEE S, LEE H, et al. X-CANIDS: Signal-aware explainable intrusion detection system for controller area network-based in-vehicle network[J]. IEEE Transactions on Vehicular Technology, 2024, 73(3): 3230–3246. doi: 10.1109/TVT.2023.3327275.
    [24]
    WANG Kai, JIANG Qiguang, WANG Bailing, et al. StatGraph: Effective in-vehicle intrusion detection via multi-view statistical graph learning[J]. IEEE Transactions on Mobile Computing, 2026, 25(5): 6335–6351. doi: 10.1109/TMC.2025.3636517.
    [25]
    ZHANG Aiheng, SUN Zhen, JIANG Qiguang, et al. LiPar: A lightweight parallel learning model for practical in-vehicle network intrusion detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2025, 26(12): 23358–23373. doi: 10.1109/TITS.2025.3605465.
    [26]
    JIANG Qiguang, WANG Kai, WEI Yuliang, et al. XIPHOS: Adaptive in-vehicle intrusion detection via unsupervised graph contrastive learning[J]. IEEE Transactions on Information Forensics and Security, 2025, 20: 10419–10433. doi: 10.1109/TIFS.2025.3616624.
    [27]
    LI Sifan, CAO Yue, ZHANG Yu’ang, et al. A cloud collaborative-based intrusion detection and prevention system for IVN[J]. IEEE Transactions on Cognitive Communications and Networking, 2025, 11(4): 2768–2785. doi: 10.1109/TCCN.2024.3516052.
    [28]
    ALTHUNAYYAN M, JAVED A, and RANA O. A robust multi-stage intrusion detection system for in-vehicle network security using hierarchical federated learning[J]. Vehicular Communications, 2024, 49: 100837. doi: 10.1016/j.vehcom.2024.100837.
    [29]
    CAO Jinhui, DI Xiaoqiang, LIU Xu, et al. Anomaly detection for in-vehicle network using self-supervised learning with vehicle-cloud collaboration update[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(7): 7454–7466. doi: 10.1109/TITS.2024.3351438.
    [30]
    DING Xiaohan, ZHANG Xiangyu, MA Ningning, et al. RepVGG: Making VGG-style ConvNets great again[C]. The 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, USA, 2021: 13728–13737. doi: 10.1109/CVPR46437.2021.01352.
    [31]
    WANG Junyi, LI Zi’ao, LIU Bangli, et al. High-performance inference graph convolutional networks for skeleton-based action recognition[J]. Neurocomputing, 2025, 653: 131078. doi: 10.1016/j.neucom.2025.131078.
    [32]
    RUFF L, VANDERMEULEN R A, GÖRNITZ N, et al. Deep one-class classification[C]. The 35th International Conference on Machine Learning, Stockholm, Sweden, 2018: 4393–4402.
    [33]
    DENG Zhouyan, XUN Yijie, LIU Jiajia, et al. A novel intrusion detection system for next generation in-vehicle networks[C]. GLOBECOM 2022-2022 IEEE Global Communications Conference, Rio de Janeiro, Brazil, 2022: 2098–2103. doi: 10.1109/GLOBECOM48099.2022.10000766.
    [34]
    SONG H M, WOO J, and KIM H K. In-vehicle network intrusion detection using deep convolutional neural network[J]. Vehicular Communications, 2020, 21: 100198. doi: 10.1016/j.vehcom.2019.100198.
    [35]
    SONG Jiaru, QIN Guihe, LIANG Yanhua, et al. DGIDS: Dynamic graph-based intrusion detection system for CAN[J]. Computers & Security, 2024, 147: 104076. doi: 10.1016/j.cose.2024.104076.
    [36]
    KALKAN S C and SAHINGOZ O K. In-vehicle intrusion detection system on controller area network with machine learning models[C]. 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kharagpur, India, 2020: 1–6. doi: 10.1109/ICCCNT49239.2020.9225442.
    [37]
    GOLOVKO V and VAITSEKHOVICH L. Neural network approaches for intrusion detection and recognition[J]. International Journal of Computing, 2014, 5(3): 118–125. doi: 10.47839/ijc.5.3.416.
    [38]
    BERGER I, RIEKE R, KOLOMEETS M, et al. Comparative study of machine learning methods for in-vehicle intrusion detection[C]. ESORICS 2018 International Workshops Computer Security, Barcelona, Spain, 2018: 85–101. doi: 10.1007/978-3-030-12786-2_6.
    [39]
    TAN Mingxing and LE Q. EfficientNet: Rethinking model scaling for convolutional neural networks[C]. The 36th International Conference on Machine Learning, Long Beach, USA, 2019: 6105–6114.
    [40]
    HOWARD A, SANDLER M, CHEN Bo, et al. Searching for MobileNetV3[C]. The 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019: 1314–1324. doi: 10.1109/ICCV.2019.00140.
    [41]
    HANSELMANN M, STRAUSS T, DORMANN K, et al. CANet: An unsupervised intrusion detection system for high dimensional CAN bus data[J]. IEEE Access, 2020, 8: 58194–58205. doi: 10.1109/ACCESS.2020.2982544.
    [42]
    ZONG Bo, SONG Qi, MIN M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]. The 6th International Conference on Learning Representations, Vancouver, Canada, 2018.
    [43]
    ZHOU Yixuan, XU Xing, SONG Jingkuan, et al. MSFlow: Multiscale flow-based framework for unsupervised anomaly detection[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(2): 2437–2450. doi: 10.1109/TNNLS.2023.3344118.
    [44]
    ZHOU Qihang, HE Shibo, LIU Haoyu, et al. Label-free multivariate time series anomaly detection[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3166–3179. doi: 10.1109/TKDE.2024.3349613.
    [45]
    YANG Yiyuan, ZHANG Chaoli, ZHOU Tian, et al. DCdetector: Dual attention contrastive representation learning for time series anomaly detection[C]. The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, USA, 2023: 3033–3045.
    [46]
    FANG Yuchen, XIE Jiandong, ZHAO Yan, et al. Temporal-frequency masked autoencoders for time series anomaly detection[C]. 2024 IEEE 40th International Conference on Data Engineering (ICDE), Utrecht, Netherlands, 2024: 1228–1241. doi: 10.1109/ICDE60146.2024.00099.
    [47]
    苗金钊, 刘金良, 孙乐, 等. 基于虚假数据检测的信息物理系统安全学习控制方法[J]. 电子与信息学报, 2026, 48(4): 1434–1443. doi: 10.11999/JEIT250537.

    MIAO Jinzhao, LIU Jinliang, SUN Le, et al. A learning-based security control method for cyber-physical systems based on false data detection[J]. Journal of Electronics & Information Technology, 2026, 48(4): 1434–1443. doi: 10.11999/JEIT250537.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(4)  / Tables(8)

    Article Metrics

    Article views (360) PDF downloads(25) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return