A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks
Paper in proceeding, 2025
A multi-similarity Siamese neural network unifies zero-day anomaly detection and one-shot classification in optical networks, achieving over 99% accuracy and instant adaptability across lightpaths and unseen anomaly types without any retraining.
Machine learning
Anomaly detection
Optical networks
Anomaly classification
Artificial intelligence
Contrastive learning
Author
Carlos Natalino Da Silva
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Flávia Pessoa Monteiro
Federal University of Western Pará (UFOPA)
Paolo Monti
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Proceedings of the Optical Fiber Communication Conference (OFC) 2026
M3A
Optical Fiber Communication Conference (OFC) 2026
Los Angeles, CA, USA,
Los Angeles, CA, USA,
Areas of Advance
Information and Communication Technology
Subject Categories (SSIF 2025)
Communication Systems
Computer Sciences
Telecommunications
Related datasets
Optical network soft failure dataset [dataset]
URI: https://data.mendeley.com/datasets/y3pspy7j83/1 DOI: 10.17632/y3pspy7j83.1