Illegal Fishing Detection Based on the Anomalous AIS Signals Using Deep Learning

DOI

10.2991/978-94-6239-616-6_89How to use a DOI?

Keywords

Self-Supervised Transformer Networks; AIS Signal Forensics; Spatio-Temporal Trajectory Modeling; Maritime Anomaly Detection; IUU Vessel Surveillance; Signal Suppression Analytics

Abstract

Illegal, Unreported and Unregulated (IUU) fishing continues to harm marine ecosystems and affect global food stability. Vessels involved in such activities often hide their real movement by turning off, altering or spoofing their Automatic Identification System (AIS) signals. Detecting this type of behaviour is difficult because labelled datasets of AIS manipulation are extremely rare, and vessel movements vary widely with time and environment. To address this, the study introduces a self-supervised transformer model that learns normal AIS patterns from large AIS datasets (25–50 GB) without needing labels. The model predicts the expected AIS transmission using spatial and temporal vessel movements, and any unusual difference between the predicted and actual signal is marked as a possible anomaly. This helps distinguish natural disturbances from intentional AIS suppression. The model achieved an accuracy of 92.8%, performing better than common methods such as SVM, Random Forest, LSTM and Autoencoders. Since the system outputs simple CSV and console logs, it can be deployed easily in real-time maritime surveillance environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - T. Rakesh
AU  - S. Krishna Prasath
AU  - C. Illakiyavarshini
PY  - 2026
DA  - 2026/03/31
TI  - Illegal Fishing Detection Based on the Anomalous AIS Signals Using Deep Learning
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1211
EP  - 1224
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_89
DO  - 10.2991/978-94-6239-616-6_89
ID  - Rakesh2026
ER  -