Variational Autoencoder Domain Adaptation for Cross-System Generalization in ML-Based SOP Monitoring

TL;DR

This paper introduces a VAE-based domain adaptation framework that significantly improves cross-system generalization in ML-based optical fiber threat detection, outperforming traditional methods.

Contribution

The novel VAE-based domain adaptation method learns shared representations across different optical systems, enhancing cross-system threat detection accuracy.

Findings

Achieves 95.3% accuracy from System 1 to System 2

Achieves 73.5% accuracy from System 2 to System 1

Gains of 83.4% and 51% over baseline DNNs

Abstract

Machine learning (ML) models trained to detect physical-layer threats on one optical fiber system often fail catastrophically when applied to a different system, due to variations in operating wavelength, fiber properties, and network architecture. To overcome this, we propose a Domain Adaptation (DA) framework based on a Variational Autoencoder (VAE) that learns a shared representation capturing event signatures common to both systems while suppressing system-specific differences. The shared encoder is first trained on the combined data from two distinct optical systems: a 21 km O-band dark-fiber testbed (System 1) and a 63.4 km C-band live metro ring (System 2). The encoder is then frozen, and a classifier is trained using labels from an individual system. The proposed approach achieves 95.3% and 73.5% cross-system accuracy when moving from System 1 to System 2 and vice versa, respectively. This corresponds to gains of 83.4% and 51% over a fully supervised Deep Neural Network (DNN) baseline trained on a single system, while preserving intra-system performance.