Federated Learning for Anomaly Detection in Maritime Movement Data

TL;DR

This paper presents M3fed, a federated learning approach for maritime movement anomaly detection that enhances data privacy and reduces communication costs, demonstrated through experiments on AIS data.

Contribution

The paper introduces M3fed, a novel federated learning framework specifically designed for maritime anomaly detection, with new strategies for training and evaluation.

Findings

M3fed reduces communication costs compared to centralized models

M3fed maintains comparable anomaly detection accuracy

Federated approach enhances data privacy in maritime data analysis

Abstract

This paper introduces M3fed, a novel solution for federated learning of movement anomaly detection models. This innovation has the potential to improve data privacy and reduce communication costs in machine learning for movement anomaly detection. We present the novel federated learning (FL) strategies employed to train M3fed, perform an example experiment with maritime AIS data, and evaluate the results with respect to communication costs and FL model quality by comparing classic centralized M3 and the new federated M3fed.