Work

Machine Learning-Based Polarization Signature Analysis for Detection and Categorization of Eavesdropping and Harmful Events

Year: 2024

Type: conference-paper

Abstract: We propose a methodology that uses polarization state changes and machine learning to detect and classify eavesdropping, harmful, and non-harmful events in the optical fiber network. Our solution achieves 92.3% accuracy over 13 experimental scenarios.

Source: Optical Fiber Communication Conference

DOI: 10.1364/ofc.2024.m1h.1

Authors: Leyla Sadighi, Stefan Karlsson, Carlos Natalino, Marija Furdek

Institutions: Chalmers University of Technology, Defence Materiel Administration

Language: English

Topic: Optical Network Technologies

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: bronze

Funders: VINNOVA, Vetenskapsrådet, Eurostars

Awards: EUREKA CELTIC AI-NET PROTECT, Safeguarding optical communication networks from cyber-security attacks