A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks
Paper i 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.
Författare
Carlos Natalino Da Silva
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
Flávia P. Monteiro
Universidade Federal do Oeste do Pará (UFOPA)
Paolo Monti
Chalmers, Elektroteknik, Kommunikation, Antenner och Optiska Nätverk
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,
Ämneskategorier (SSIF 2025)
Datavetenskap (datalogi)
DOI
10.1364/OFC.2026.M3A.2