Dark Activity Detection in AIS-Based Maritime Networks

Abstract

The Automated Identification System (AIS) is an indispensable tracking system employed in the maritime industry for vessel identification, location tracking, and collision avoidance. While AIS messages provide essential information for maritime traffic management, they also present challenges when vessels aim to conduct operations discreetly or evade observation. This phenomenon, referred to as "dark activity", involves intentional AIS deactivation by vessel operators seeking to conceal their actions, often related to illicit or illegal maritime activities such as smuggling, piracy or illegal fishing. The detection and monitoring of dark activities pose significant challenges for law enforcement and security agencies. This paper explores innovative approaches to address this issue by harnessing AIS data and incorporating rule-based techniques, as well as machine learning techniques to enhance maritime security efforts. We adopted a local approach where a dark activity of a vessel is detected by nearby ships depending on the previous signals. We implemented a detailed simulation environment based on real and realistic data to run the proposed algorithms. Simulation results show that while rule-based approach is successful in detecting dark activities, it tends to produce false alarms, and ML-based approach provides better overall accuracy.

Keywords

• automatic identification system
• maritime networks
• dark activity detection