Secure and reliable data communication in optical networks is critical for high-speed internet. We propose a data driven approach for the anomaly detection and faults identification in optical networks to diagnose physical attacks such as fiber breaks and optical tapping. The proposed methods include an autoencoder-based anomaly detection and an attention-based bidirectional gated recurrent unit algorithm for the fiber fault identification and localization. We verify the efficiency of our methods by experiments under various attack scenarios using real operational data.
@article{arxiv.2202.11756,
title = {ML-based Anomaly Detection in Optical Fiber Monitoring},
author = {Khouloud Abdelli and Joo Yeon Cho and Carsten Tropschug},
journal= {arXiv preprint arXiv:2202.11756},
year = {2022}
}
Comments
The AAAI-22 Workshop on Artificial Intelligence for Cyber Security (AICS)