Machine Learning for Intrusion Detection and Trust Management in Vehicular Ad-Hoc Networks: A Focused Review (2023-2025)
DOI:
https://doi.org/10.31642/JoKMC/2018/130202Keywords:
Vehicular Ad-Hoc Networks (VANETs), Intrusion Detection, Trust Management, Sybil Attack Detection, Machine Learning, Deep Learning, V2X SecurityAbstract
Abstract—Vehicular Ad-Hoc Networks (VANETs) provide the ultra-low-latency Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) links that underpin next-generation intelligent transportation systems. The same open wireless medium, however, renders VANETs vulnerable to a broad spectrum of cyber-attacks, from denial-of-service floods and replay injections to Sybil-based trust manipulation. While several surveys published before 2023 examined either intrusion detection or trust evaluation in isolation, none has jointly analysed both domains within the rapidly evolving machine-learning (ML) landscape. Addressing this gap, the present review offers the first integrated synthesis (2023-2025) of ML-driven intrusion detection and trust management for VANET security. State-of-the-art ML contributions are then organised into three focal tracks: (i) supervised and unsupervised intrusion-detection systems for V2X links; (ii) misbehaviour-, reputation-, and Sybil-node detection schemes that quantify inter-vehicle trust; and (iii) collaborative and federated learning approaches that distribute model training across vehicles and RSUs to conserve bandwidth and protect privacy. For each track, the review compares leading techniques with respect to datasets (e.g., VeReMi, SUMO/OMNeT++ traces), feature engineering pipelines, model families (CNN/LSTM, graph neural networks, hybrid ensembles), resource footprint, and reported performance, highlighting that many recent models exceed 95 % detection accuracy while maintaining real-time inference. A consolidated comparison table distils trade-offs among detection rate, false-positive rate, computational overhead, and explainability, thereby guiding practitioners in architecture selection. The analysis further exposes persistent gaps: scarcity of large, standardised datasets; susceptibility of ML models to physics-informed adversarial examples; limited frameworks for fusing intrusion evidence with trust scores; and the absence of lightweight yet adaptive models suitable for resource-constrained on-board units.
Downloads
References
[1] T. Yang, R. Sun, R. S. Rathore, and I. Baig, “Enhancing Cybersecurity and Privacy Protection for Cloud Computing-Assisted Vehicular Network of Autonomous Electric Vehicles: Applications of Machine Learning,” World Electric Vehicle Journal, vol. 16, no. 1, p. 14, Dec. 2024, doi: https://doi.org/10.3390/wevj16010014 .
[2] C. Jayasri, V. Balaji, C. M. Nalayini, and S. Pradeep, “Detecting cyber attacks in vehicle networks using improved LSTM based optimization methodology,” Scientific Reports, vol. 15, no. 1, May 2025, doi: https://doi.org/10.1038/s41598-025-04643-8.
[3] R. Rai, J. Grover, P. Sharma, and A. Pareek, “Securing the CAN bus using deep learning for intrusion detection in vehicles,” Scientific Reports, vol. 15, no. 1, Apr. 2025, doi: https://doi.org/10.1038/s41598-025-98433-x.
[4] E. Alalwany and I. Mahgoub, “Security and Trust Management in the Internet of Vehicles (IoV): Challenges and Machine Learning Solutions,” Sensors, vol. 24, no. 2, p. 368, Jan. 2024, doi: https://doi.org/10.3390/s24020368.
[5] W. Zhao, Y. Yang, H. Hu, Y. Chen, and F. Yu, “A lightweight intrusion detection approach for CAN bus using depthwise separable convolutional Kolmogorov Arnold network,” Scientific Reports, vol. 15, no. 1, May 2025, doi: https://doi.org/10.1038/s41598-025-02474-1.
[6] H. Yang and M. Effatparvar, “A deep learning based intrusion detection system for CAN vehicle based on combination of triple attention mechanism and GGO algorithm,” Scientific Reports, vol. 15, no. 1, Jun. 2025, doi: https://doi.org/10.1038/s41598-025-04720-y. 14
[7] Meghana R, Sowmyashree Sakrepatna Ramesha, and A. Mukhopadhyay, “QCAE-QOC-SVM: A Hybrid Quantum Machine Learning Model for DoS and Fuzzy Attack Detection on Autonomous Vehicle CAN Bus,” MethodsX, vol. 15, no. 103471, pp. 103471-103471, Jun. 2025, doi: https://doi.org/10.1016/j.mex.2025.103471.
[8] S. Jeong, S. Lee, H. Lee, and H. K. Kim, “X-CANIDS: Signal-Aware Explainable Intrusion Detection System for Controller Area Network-Based In-Vehicle Network,” IEEE Transactions on Vehicular Technology, vol. 73, no. 3, pp. 3230-3246, Mar. 2024, doi: https://doi.org/10.1109/tvt.2023.3327275.
[9] M. Ababsá, S. Ribouh, A. Malki, and L. Khoukhi, “Deep Multimodal Learning for Real-Time DDoS Attacks Detection in Internet of Vehicles,” ICC 2025, pp. 3039-3044, doi: https://doi.org/10.1109/ICC52391.2025.11160909.
[10] M. A. Elsadig et al., “Connected Vehicles Security: A Lightweight Machine Learning Model to Detect VANET Attacks,” World Electric Vehicle Journal, vol. 16, no. 6, p. 324, Jun. 2025, doi: https://doi.org/10.3390/wevj16060324.
[11] S. Alshathri, A. Sayed, and E. E.-D. Hemdan, “An Intelligent Attack Detection Framework for the Internet of Autonomous Vehicles with Imbalanced Car Hacking Data,” World Electric Vehicle Journal, vol. 15, no. 8, p. 356, Aug. 2024, doi: https://doi.org/10.3390/wevj15080356.
[12] N. Ahmed, F. Hassan, K. Aurangzeb, A. H. Magsi, and M. Alhussein, “Advanced machine learning approach for DoS attack resilience in internet of vehicles security,” Heliyon, vol. 10, no. 8, p. e28844, Apr. 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e28844.
[13] A. Manderna, S. Kumar, U. Dohare, M. Aljaidi, O. Kaiwartya, and J. Lloret, “Vehicular Network Intrusion Detection Using a Cascaded Deep Learning Approach with Multi-Variant Metaheuristic,” Sensors, vol. 23, no. 21, p. 8772, Oct. 2023, doi: https://doi.org/10.3390/s23218772.
[14] H. Babbar, S. Rani, and M. Driss, “Effective DDoS attack detection in software-defined vehicular networks using statistical flow analysis and machine learning,” PLOS ONE, vol. 19, no. 12, p. e0314695, Dec. 2024, doi: https://doi.org/10.1371/journal.pone.0314695.
[15] I. Mahmoudi, D. Boubiche, S. Athmani, H. Toral-Cruz, and F. Chan-Puc, “Academic Editors: Olusola Tolulope Odeyomi and Temitayo Olowu Toward Generative AI-Based Intrusion Detection Systems for the Internet of Vehicles (IoV),” Future Internet, vol. 17, no. 310, 2025, doi: https://doi.org/10.3390/fi17070310.
[16] Y. Zhu et al., “Sybil Attacks Detection and Traceability Mechanism Based on Beacon Packets in Connected Automobile Vehicles,” Sensors, vol. 24, no. 7, p. 2153, Jan. 2024, doi: https://doi.org/10.3390/s24072153.
[17] T. L. Morton, A. Borah, and A. Paranjothi, “Trust‐Aware Sybil Attack Detection for Resilient Vehicular Communication,” Internet Technology Letters, Nov. 2024, doi: https://doi.org/10.1002/itl2.617.
[18] A. Badshah et al., “Blockchain-Assisted Lightweight Authenticated Key Agreement Security Framework for Smart Vehicles-Enabled Intelligent Transportation System,” IEEE Transactions on Automation Science and Engineering, vol. 21, no. 3, pp. 2425-2439, Jul. 2024, doi: https://doi.org/10.1109/tase.2024.3381068.
[19] F. G. Abdulkadhim, Z. Yi, C. Tang, A. N. Onaizah and A. H. Radie, "Optimizing Roadside via Unit Deployment Mechanism in V ANET," 2020 3rd International Conference on Engineering Technology and its Applications (IICETA), Najaf, Iraq, 2020, pp. 144-149, doi: 10.1109/IICETA50496.2020.9318821.
[20] Muzun Althunayyan, A. Javed, and O. Rana, “A robust multi-stage intrusion detection system for in-vehicle network security using hierarchical federated learning,” Vehicular Communications, vol. 49, pp. 100837-100837, Aug. 2024, doi: https://doi.org/10.1016/j.vehcom.2024.100837.
[21] K. Rashid, Y. Saeed, A. Ali, F. Jamil, R. Alkanhel, and A. Muthanna, “An Adaptive Real-Time Malicious Node Detection Framework Using Machine Learning in Vehicular Ad-Hoc Networks (VANETs),” Sensors, vol. 23, no. 5, p. 2594, Feb. 2023, doi: https://doi.org/10.3390/s23052594.
[22] U. Demir, Y. Sagduyu, T. Erpek, H. Jafari, S. Kompella, and M. Xue, “Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats,” 2025, doi: https://doi.org/10.1145/3733965.3733967. 15
[23] F. Hassan et al., “A hybrid approach for intrusion detection in vehicular networks using feature selection and dimensionality reduction with optimized deep learning,” PLOS ONE, vol. 20, no. 2, p. e0312752, Feb. 2025, doi: https://doi.org/10.1371/journal.pone.0312752.
[24] M. Alotaibi et al., “Integrating Two-Tier Optimization Algorithm with Convolutional Bi-LSTM Model for Robust Anomaly Detection in Autonomous Vehicles,” IEEE Access, pp. 1-1, Jan. 2024, doi: https://doi.org/10.1109/access.2024.3523539.
[25] A. Haydari and Y. Yilmaz, “RSU-Based Online Intrusion Detection and Mitigation for VANET,” Sensors, vol. 22, no. 19, p. 7612, Oct. 2022,doi:https://doi.org/10.3390/s22197612.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 Mohammad Abbas Alkifaee, Fahad Ghalib Abdulkadhim
This work is licensed under a Creative Commons Attribution 4.0 International License.
which allows users to copy, create extracts, abstracts, and new works from the Article, alter and revise the Article, and make commercial use of the Article (including reuse and/or resale of the Article by commercial entities), provided the user gives appropriate credit (with a link to the formal publication through the relevant DOI), provides a link to the license, indicates if changes were made and the licensor is not represented as endorsing the use made of the work.
How to Cite
