Deukjae Cho

Sanghyeon Park, DeukJae Cho, Pyo-Woong Son

Global Navigation Satellite System (GNSS) spoofing and jamming threaten maritime navigation by corrupting positions from Automatic Identification System (AIS) transponders. Crucially, raw AIS messages contain communication-layer defects (duplicated MMSIs, timestamp errors, stale retransmissions, and multi-station rebroadcast delays) that can mimic spoofing or jamming. Thus, AIS positions are unreliable without pre-filtering. We propose a three-stage AIS-based framework that (1) uses rule-based diagnostics to discard communication faults, (2) applies an interacting multiple model filter and transmission-interval analysis to extract kinematic-consistency and continuity anomalies, and (3) applies spatiotemporal DBSCAN to group anomalies by multi-vessel coherence and temporal persistence and classify them as sensor faults, spoofing, or jamming. Tested on approximately 966 million AIS messages from Korean coastal waters, the framework detected 17 spoofing and 343 jamming clusters and reduced false alarms by 98.6% relative to naive clustering. These results show that, after rigorous pre-filtering, AIS data can enable wide-area GNSS interference detection without dedicated sensors.

Hyobin Park, Jinwook Jung, Minseok Seo et al.

With the increase in maritime traffic and the mandatory implementation of the Automatic Identification System (AIS), the importance and diversity of maritime traffic analysis tasks based on AIS data, such as vessel trajectory prediction, anomaly detection, and collision risk assessment, is rapidly growing. However, existing approaches tend to address these tasks individually, making it difficult to holistically consider complex maritime situations. To address this limitation, we propose a novel framework, AIS-LLM, which integrates time-series AIS data with a large language model (LLM). AIS-LLM consists of a Time-Series Encoder for processing AIS sequences, an LLM-based Prompt Encoder, a Cross-Modality Alignment Module for semantic alignment between time-series data and textual prompts, and an LLM-based Multi-Task Decoder. This architecture enables the simultaneous execution of three key tasks: trajectory prediction, anomaly detection, and risk assessment of vessel collisions within a single end-to-end system. Experimental results demonstrate that AIS-LLM outperforms existing methods across individual tasks, validating its effectiveness. Furthermore, by integratively analyzing task outputs to generate situation summaries and briefings, AIS-LLM presents the potential for more intelligent and efficient maritime traffic management.