Keywords
shipboard communication
network anomaly detection
ensemble learning
SHAP
explainable AI
AIS security
port network security
Abstract
Modern maritime communication networks connect shipboard sensors, navigation systems, port operation platforms, satellite links, and shore-based control centers. Abnormal traffic in these networks may indicate spoofed navigation messages, unauthorized remote access, denial-of-service attacks, or compromised vessel communication equipment. This study proposes an interpretable hybrid ensemble learning method for anomaly detection in maritime communication networks. The framework integrates Random Forest, Histogram Gradient Boosting, and XGBoost classifiers to improve robustness under unstable link conditions, while SHAP analysis is used to explain the contribution of communication and traffic behavior features. Experiments are conducted using a maritime network testbed containing 28 vessel communication terminals, 12 port-side access gateways, and 4 satellite communication simulators. The dataset includes 2.94 million labeled traffic records collected across 18 simulated voyage and port-docking scenarios, including normal AIS message exchange, remote monitoring, bandwidth congestion, port scanning, spoofed message bursts, and unauthorized command traffic. A total of 51 features are extracted, including AIS message frequency, packet delay variation, uplink-downlink byte ratio, session restart count, retransmission density, remote access interval, and abnormal destination concentration. The proposed model achieves 97.69% accuracy, 96.81% macro-F1, and 98.34% AUC across six traffic categories. Compared with standalone XGBoost, the ensemble framework improves macro-F1 by 2.06% and reduces missed detection of spoofed message bursts by 3.74%. SHAP interpretation shows that abnormal AIS message frequency, sudden retransmission density, high uplink byte ratio, and repeated short remote sessions are the most influential indicators of maritime network anomalies. These findings suggest that explainable ensemble learning can support transparent security monitoring for shipboard and port communication infrastructures.
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).
Bruno, M. A., & Ayyappan, V. (2025). Exploring Pervasive Computing Models to Improve Crew Connectivity and Safety in Global Shipping Routes. J. Wirel. Mob. Networks Ubiquitous Comput. Dependable Appl., 16(3).
Melnyk, O., Onyshchenko, S., Onishchenko, O., Pavlova, N., Sagaydak, O., Burlachenko, D., & Koryakin, K. (2025). Strategic Decision-Making and Risk Management Approach in Autonomous Maritime systems. Journal of Maritime Research, 22(3), 50-58.
Zhu, W., Yao, Y., & Yang, J. (2025). Optimizing Financial Risk Control for Multinational Projects: A Joint Framework Based on CVaR-Robust Optimization and Panel Quantile Regression.
Anila, D., Houxiang, Z., Pero, V., & Li, G. (2026). Exploring Recent Maritime Research on AIS-Based Ship Behavior Analysis and Modeling. Journal of marine science and engineering, 14(8), 712.
Xu, S., Ma, Q., Liu, H., & Yue, L. (2026). Continuous Reorganization and Performance Preservation of Agent Memory Structure Under Distributed Change Environments.
Gomola, A., Kristensen, S. D., & Utne, I. B. (2025). Multi-level risk classification of distributed embedded software failures for autonomous systems. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 239(5), 936-965.
Huang, R. (2026). ConfSched: Confidence-Threshold Routing for Efficient Edge-Cloud Activity Recognition. World Journal of Engineering and Technology, 14(2), 471-486.
Aparcana-Tasayco, A. J., Deng, X., & Park, J. H. (2025). A systematic review of anomaly detection in IoT security: towards quantum machine learning approach. EPJ Quantum Technology, 12(1), 112.
Li, Y., & Liu, S. (2026, May). A Study on Dynamic Optimization of Alerting Policies and Multi-Agent Decision-Making Mechanisms in Cloud Environments. In 2026 7th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) (pp. 703-706). IEEE.
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.
Kirichevskaya, A. (2025). A network capacity perspective on digital signatures for AIS (Doctoral dissertation, Technische Universität Wien).
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.
Jagadhabi, N. (2025). Machine Learning Approaches for Detecting Configuration Errors in SAP Systems. Journal of Wireless Intelligence and Spectrum Engineering, 38-42.
Yang, J. (2026). Stage‐Coupled Computational Framework for Stratified Accessibility and Equity Analysis in Community‐Based Elderly Care Services.
Vaarandi, R., Tsiopoulos, L., Visky, G., Rehman, M. U., & Bahşi, H. (2025). A Systematic Literature review of Cyber security monitoring in Maritime. IEEE Access.
Deng, X., & Yang, J. (2026). Design of a Quantitative Futures Trading Model Incorporating Multimodal Feature Fusion and Tail Risk Control. Available at SSRN 6702398.
Latinopoulos, C., Zavvos, E., Kaklis, D., Leemen, V., & Halatsis, A. (2025). Marine voyage optimization and weather routing with deep reinforcement learning. Journal of Marine Science and Engineering, 13(5), 902.
Zhang, Z. (2026). A Study on Return Optimization in E-commerce for Complex Consumer Goods Driven by Installation Information Quality. Available at SSRN 6734720.
Talpur, K., Hasan, R., Gocer, I., Ahmad, S., & Bhuiyan, Z. (2025). AI in maritime security: applications, challenges, future directions, and key data sources. Information, 16(8), 658.
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.
Vasheghani, S., & Sharifi, S. (2025). Dynamic ensemble learning for robust image classification: A model-specific selection strategy. Available at SSRN 5215134.
Zi, Y., Gong, M., Xue, Z., Zou, Y., Qi, N., & Deng, Y. (2025, August). Graph neural network and transformer integration for unsupervised system anomaly discovery. In 2025 5th International Conference on Computer Science and Blockchain (CCSB) (pp. 158-162). IEEE.
Singh, K., Kashyap, A., & Cherukuri, A. K. (2025). Interpretable anomaly detection in encrypted traffic using shap with machine learning models. arXiv preprint arXiv:2505.16261.
Xue, Z., Zi, Y., Qi, N., Gong, M., & Zou, Y. (2025, August). Multi-level service performance forecasting via spatiotemporal graph neural networks. In 2025 5th International Conference on Intelligent Communications and Computing (ICICC) (pp. 202-206). IEEE.
Ahmad, F., Alasskar, A., Samui, P., & Asteris, P. G. (2025). Machine learning-based graphical user interface for predicting high-performance concrete compressive strength: comparative analysis of gradient boosting machine, random forest, and deep neural network models. Frontiers of Structural and Civil Engineering, 19(7), 1075-1090.
Zhang, Z., Gao, Y., & Tong, Y. (2026). CausalML4CX: A Causal Inference and Machine Learning Framework for Customer Experience Optimization with Application in Banking.
Qi, C., & Qiao, X. (2026). Building Reliable AI Systems: A Framework That Bridges Architecture and Operations. Available at SSRN 6795298.
Firouzi, F., Farahani, B., Firouzi, N., & Daneshmand, M. (2026). Smart and Connected Health. In Smart and Connected Health: AI, IoT, and Trustworthy Technologies (pp. 1-136). Cham: Springer Nature Switzerland.
Su, D., & Shi, X. Optimizing Family–School Collaboration to Improve Educational and Social Outcomes for Children with Intellectual Disabilities in Inclusive Public Schools.