Supervisors

Suitable for

Abstract

A key challenge for maritime security is automatically detecting and classifying ships. This is essential so that government and law enforcement agencies know where ships are and what they are up to. This way they can combat key maritime threats such as piracy, unsustainable fishing, pollution, or the smuggling of illicit goods. Due to limitations of the two main technologies used for maritime security—the automatic identification system (AIS) and synthetic aperture radar (SAR) satellite imagery—current solutions are inaccurate and often require manual intervention. AIS is a cooperative tracking system that provides precise and frequent updates of a vessel’s location and identity. But, due to the cooperative nature of AIS, ships can choose to stop participating in the system or even falsify messages that mask their location or identity. As a non-cooperative system, SAR can detect ships even if they want to remain hidden. However, SAR has its own disadvantages, including low image resolutions and infrequent updates of each location.

Students may choose to tackle this problem in one of three possible ways:

• By improving ship detection and classification systems

• By developing a transmitter fingerprinting system for AIS messages

• By leveraging RF signals to localise AIS messages

Prerequisites: This project will require knowledge in machine learning, data analysis, and a good grasp of python.

References:

For the ship classification sub project:

[1] Fernando Paolo, et al. xview3-sar: Detecting dark fishing activity using synthetic aperture radar imagery. Advances in Neural Information Processing Systems, 35, 2022.

[2] Xiyue Hou, et al. Fusar-ship: Building a high-resolution sar-ais matchup dataset of gaofen-3 for ship detection and recognition. Science China Information Sciences, 63, 2020.

For the transmitter fingerprinting sub project:

[1] Joshua Smailes et al. Watch this space: securing satellite communication through resilient transmitter fingerprinting. Conference on Computer and Communications Security, ACM, 2023. https://ora.ox.ac.uk/objects/uuid:6d23ae00-8a25-434a-952d-0908cc9a3b89

[2] Qi Jiang et al. Rf fingerprinting identification in low snr scenarios for automatic identification system. IEEE Transactions on Wireless Communications, 23:3, 2024.

For the RF localisation sub project:

[1] Eric Jedermann, et al. Orbit-based authentication using tdoa signatures in satellite networks. In Proceedings of the 14th ACM Conference on Security and Privacy in Wireless and Mobile Networks, 2021.