Sea-cret Agents: Maritime Abduction for Region Generation to Expose Dark Vessel Trajectories
Divyagna Bavikadi, Nathaniel Lee, Paulo Shakarian, Chad Parvis
TL;DR
This work tackles the challenge of locating AIS-dark maritime vessels in long-range horizons, where traditional ML approaches struggle with data efficiency and explainability. It introduces a formal abductive framework built on temporal annotated logic and rule learning to infer dark-vessel locations from partial trajectories, achieving near-full recall with substantially smaller search areas than ML baselines. Core contributions include a logic language for maritime trajectories, an abductive top-k region generation mechanism with a parsimonious scoring function, and a data-efficient rule-learning component that provides transparent, explainable predictions. The results demonstrate strong area-efficiency, robust long-horizon performance, and data efficiency, with a deployment pathway via a live, microservices-based platform for analysts to detect and investigate dark vessels in near real-time.
Abstract
Bad actors in the maritime industry engage in illegal behaviors after disabling their vessel's automatic identification system (AIS) - which makes finding such vessels difficult for analysts. Machine learning approaches only succeed in identifying the locations of these ``dark vessels'' in the immediate future. This work leverages ideas from the literature on abductive inference applied to locating adversarial agents to solve the problem. Specifically, we combine concepts from abduction, logic programming, and rule learning to create an efficient method that approaches full recall of dark vessels while requiring less search area than machine learning methods. We provide a logic-based paradigm for reasoning about maritime vessels, an abductive inference query method, an automatically extracted rule-based behavior model methodology, and a thorough suite of experiments.