Sea-cret Agents: Maritime Abduction for Region Generation to Expose Dark Vessel Trajectories

TL;DR

This paper introduces a logic-based abductive inference method to locate dark vessels in maritime regions, outperforming machine learning in recall and search efficiency by reasoning about vessel behaviors.

Contribution

It presents a novel abductive inference framework combining logic programming and rule learning for maritime vessel localization, addressing dark vessel detection challenges.

Findings

Achieves near full recall of dark vessels

Reduces search area compared to machine learning methods

Provides a logic-based reasoning paradigm for maritime vessel analysis

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.