Behavioral Pattern Mining for Securing Blockchain-Integrated IoT Gateways
DOI:
https://doi.org/10.66238/jaeee22Keywords:
V2X security, vehicular networks, network traffic anomaly detection, explainable AI, ensemble learning, SHAP, intrusion detectionAbstract
Vehicle-to-everything networks rely on continuous communication among vehicles, roadside units, and cloud-based traffic services. However, abnormal network traffic caused by spoofing, denial-of-service, and message injection attacks can affect both communication reliability and driving safety. This study proposes an explainable ensemble-based intrusion detection framework for V2X network traffic using flow-level behavioral features. The proposed method combines CatBoost, Random Forest, and Histogram Gradient Boosting through a weighted voting strategy to improve detection stability under mixed attack scenarios. SHAP analysis is introduced to explain the contribution of packet-level and session-level features to each detection decision. Experiments are conducted on the VeReMi Extension dataset and a V2X traffic subset generated from CICIDS2017, containing 1.76 million labeled communication records in total. After preprocessing, 38 traffic features are selected, including packet rate, flow duration, message frequency, source-destination byte ratio, and TCP flag distribution. The proposed model achieves 98.16% accuracy, 97.42% F1-score, and 98.89% AUC, outperforming standalone CatBoost and Random Forest models by 1.31% and 2.08% in F1-score, respectively. The false alarm rate is reduced from 3.84% to 2.17% compared with the best single-model baseline. SHAP results show that abnormal packet burst frequency, short flow duration, high destination port concentration, and asymmetric byte transfer are the most important indicators of malicious V2X traffic. The results demonstrate that explainable ensemble learning can improve both detection accuracy and decision transparency in vehicular communication security.
References
Wang, Y., Chen, J., Arias, R., Wang, Y., & Yin, X. (2026). Development and Validation of a Patient-Friendly Digital Assessment Platform for Precision Screening of Oral Anti-Obesity Medications (AOMs).
Kandali, K., Nouh, S., Bennis, L., & Bennis, H. (2026). A Comprehensive Survey on VANET–IoT Integration Toward the Internet of Vehicles: Architectures, Communications, and System Challenges. Future Transportation, 6(1), 32.
Zhu, W., Yang, J., & Yao, Y. (2025). How Cross-Departmental Collaboration Structures Mitigate Cross-Border Compliance Risks: Network Causal Inference Based on ManpowerGroup's Staffing Projects.
Noor, K., Imoize, A. L., Li, C. T., & Weng, C. Y. (2025). A review of machine learning and transfer learning strategies for intrusion detection systems in 5G and beyond. Mathematics, 13(7), 1088.
Shao, W. (2026, March). Interpretable Ensemble Learning for Network Traffic Anomaly Detection: A SHAP-based Explainable AI Framework for Embedded Systems Security. In 2026 14th International Symposium on Digital Forensics and Security (ISDFS) (pp. 1-4). IEEE.
Ahmad, T., Hadi, M. U., Vassiliou, V., Dimitriou, L., Anwar, A., & Tran, T. A. (2025). Real‐time anomaly detection in smart vehicle‐to‐UAV networks for disaster management. Transactions on Emerging Telecommunications Technologies, 36(5), e70162.
Su, D., & Zhang, H. Developing a Data-Driven Computational Framework for Scalable Special Education Practices for Autism and Intellectual Disabilities in the US Public School System.
Sridevi, K., Masood, W., Tanveer, S., Mirza, O. M., Sivakumar, N. R., & Selvarajan, S. (2026). ZuraNet: a hybrid rule-based intrusion detection system with deep learning for securing SCADA-driven cyber-physical systems. Scientific Reports.
Xu, S., Ma, Q., Liu, H., & Yue, L. (2026). Continuous Reorganization and Performance Preservation of Agent Memory Structure Under Distributed Change Environments.
Elmorsy, S. M. A., Osman, S. M., & Gamel, S. A. (2025). Enhanced spectrum sensing for 5G and LTE signals using advanced deep learning models and hyperparameter tuning. Scientific Reports, 15(1), 24825.
Ma, Y. (2026). Industrial Financial Risk Prediction Model Based on Graph Neural Network and Knowledge Graph Inference. Journal of Circuits, Systems and Computers, 35(16), 2650103.
Alalwany, E., Mahgoub, I., Alsharif, B., & Alfahaid, A. (2025). An Intelligent Ensemble-Based Detection of In-Vehicle Network Intrusion. Applied Sciences, 15(12), 6869.
Gao, G., Gao, R., Lu, C., Gao, R., & Kuang, Y. (2026, March). Security Governance Methods and Quantitative Evaluation for Enterprise SMS and Verification Code Systems. In 2026 International Conference on Generative Artificial Intelligence and Information Security (GAIIS) (pp. 455-458). IEEE.
Drǎguşin, S. A., Boştinaru, R. N., Bizon, N., & Iana, G. V. (2026). AI-Based Embedded Framework for Cyber-Attack Detection Through Signal Processing and Anomaly Analysis. Applied Sciences, 16(3), 1416.
Chen, F., Liang, H., Yue, L., Xu, P., & Li, S. (2025). Low-Power Acceleration Architecture Design of Domestic Smart Chips for AI Loads.
Sheelavant, K. K., Yamini, C., Bhushan, P., & Kumar, C. (2025). Ensemble Learning-Based Intrusion Detection and Classification for Securing IoT Networks: An Optimized Strategy for Threat Detection and Prevention. Journal of Intelligent Systems and Internet of Things, 101-118.
Liang, R., Fan, F., Liang, Y., & Li, S. (2025). Constructing an Adaptive Optimization Model for Ribbon Recommendation and Interface for User Habits.
Zou, Y., Qi, N., Deng, Y., Xue, Z., Gong, M., & Zhang, W. (2025, July). Autonomous resource management in microservice systems via reinforcement learning. In 2025 8th International Conference on Computer Information Science and Application Technology (CISAT) (pp. 991-995). IEEE.
Sankar, S. R., & Jothi, B. (2026). EGOA-DL-IDS: explainable intrusion detection in SDN-based industrial cyber physical system with optimized deep learning techniques. Cluster Computing, 29(4), 242.
Yin, J., Huang, Y., & Rao, H. (2026). A Study on the Dynamic Evolution of Learning Behavior and Outcome Prediction in Digital Educational Environments. Available at SSRN 6607139.
Edo, G., Ahmad, T., & Putra, M. A. R. (2025). Hybrid GAN-LSTM for Enhancing DDoS Detection on Imbalance Dataset. International Journal of Safety & Security Engineering, 15(1).
Deng, X., & Yang, J. (2026). Design of a Quantitative Futures Trading Model Incorporating Multimodal Feature Fusion and Tail Risk Control. Available at SSRN 6702398.
Baharlouei, H., Makanju, A., & Zincir-Heywood, N. (2026). Comprehensive host-based malicious behaviour detection in vanets. Journal of Network and Systems Management, 34(4), 100.
Zhang, Z. (2026). A Study on the Identification of Manipulative Design in Subscription and Payment Interfaces of Digital Consumer Platforms and Its Behavioral Effects. Available at SSRN 6734760.
Aloqaily, A., Abdallah, E. E., Baarah, A., Alnabhan, M., Alshdaifat, E. A., & Milhem, H. (2025). Optimized Hybrid Ensemble Intrusion Detection for VANET-Based Autonomous Vehicle Security. Network, 5(4), 43.
Zhang, Z., Tong, Y., & Gao, Y. (2026). Retrieval-Augmented Generation with Low-Latency Deployment for Vertical Domains Question Answering: A Case Study on Economic Resource Platforms.
Ibrahim, N., Rajalakshmi, N. R., Sivakumar, V., & Sharmila, L. (2025). An optimized hybrid ensemble machine learning model combining multiple classifiers for detecting advanced persistent threats in networks. Journal of Big Data, 12(1), 212.
Qi, C., & Qiao, X. (2026). Efficient Data Sampling and Feature Selection Algorithms for Scalable Machine Learning Pipelines.
Taheri, R., Gegov, A., Arabikhan, F., Ichtev, A., & Georgieva, P. (2025, November). Explainable Artificial Intelligence for Intrusion Detection in Connected Vehicles. In Principle and Practice of Data and Knowledge Acquisition Workshop (pp. 162-176). Singapore: Springer Nature Singapore.
Huang, R. (2026). ConfSched: Confidence-Threshold Routing for Efficient Edge-Cloud Activity Recognition. World Journal of Engineering and Technology, 14(2), 471-486.
Bari, B. S., Puthal, D., & Yelamarthi, K. (2025). Datasets in vehicular communication systems: A review of current trends and future prospects. SN Computer Science, 6(3), 210.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 James Walker, Sophie Harris, Benjamin Clarke
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of Advanced Electrical and Electronic Engineering (JAEEE) are distributed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). Authors retain copyright of their work while granting the journal the right of first publication.
Under this license, users are permitted to read, download, copy, distribute, print, share, adapt, and reuse published material for both commercial and non-commercial purposes, provided appropriate credit is given to the original author(s), the source of publication is acknowledged, a link to the license is provided, and any changes made are clearly indicated.
The license does not permit users to imply endorsement by the original authors or the journal. No additional restrictions may be imposed that prevent others from exercising the rights granted under CC BY 4.0.
By submitting to the journal, authors confirm that their work is original, does not infringe upon third-party rights, and complies with ethical publishing standards.
