Reliable vessel identity verification for maritime traffic systems using AIS physical features

Reliable vessel identification is fundamental to maritime traffic safety and effective supervision. However, the Maritime Mobile Service Identity (MMSI) embedded in Automatic Identification System (AIS) messages can be deliberately altered, which compromises the integrity of situational awareness and poses risks to traffic management. To address this limitation, this study investigates vessel identity verification based on physical features inherent in AIS signals, shifting the focus from message-level identifiers to signal-level characteristics. A verification framework is developed by extracting stable physical features associated with onboard transmission hardware and the surrounding electromagnetic environment. To enhance discriminability, a feature fusion scheme is introduced to integrate complementary signal characteristics under varying channel conditions. In addition, a metric-constrained representation strategy is adopted to improve intra-class compactness and inter-class separability in the feature space. For decision-making, a hybrid criterion combining distance-based scoring with confidence control is employed, enabling both the reliable identification of known vessels and the effective rejection of previously unseen targets. The proposed approach is validated using AIS data collected in a port environment. The experimental results show that the method achieves an identification accuracy of 97.5% for known vessels while maintaining a rejection rate exceeding 90% for unknown vessels. The performance remains stable under complex and variable operating conditions. These findings demonstrate that AIS physical features provide a robust and reliable basis for vessel identity verification. The proposed framework offers a practical pathway to enhance the credibility of maritime traffic data and supports safer and more effective maritime governance.