A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks
Paper in proceeding, 2026
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.
Author
Carlos Natalino Da Silva
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Flávia P. Monteiro
Federal University of Western Pará (UFOPA)
Paolo Monti
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
2026 Optical Fiber Communications Conference and Exhibition Ofc 2026 Proceedings
9781957171548 (ISBN)
2026 Optical Fiber Communications Conference and Exhibition, OFC 2026
Los Angeles, USA,
Los Angeles, USA,
Subject Categories (SSIF 2025)
Computer Sciences
DOI
10.1364/OFC.2026.M3A.2