ML-based Anomaly Detection in Optical Fiber Monitoring
This work addresses the need for secure and reliable data communication in optical networks, but it appears incremental as it applies existing ML techniques to a specific domain.
The paper tackled the problem of detecting and identifying physical attacks like fiber breaks and optical tapping in optical networks, achieving verification of their methods' efficiency through experiments with real operational data under various attack scenarios.
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.