Machine Learning-Based Polarization Signature Analysis for Detection and Categorization of Eavesdropping and Harmful Events
Paper in proceeding, 2024
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.
Author
Leyla Sadighi
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Stefan Karlsson
Swedish Defence Materiel Administration
Carlos Natalino Da Silva
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Marija Furdek Prekratic
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
2024 Optical Fiber Communications Conference and Exhibition, OFC 2024 - Proceedings
9781957171326 (ISBN)
2024 Optical Fiber Communications Conference and Exhibition, OFC 2024
San Diego, USA,
San Diego, USA,
Providing Resilient & secure networks [Operating on Trusted Equipment] to CriTical infrastructures (PROTECT)
VINNOVA (2020-03506), 2021-02-01 -- 2024-01-31.
Safeguarding optical communication networks from cyber-security attacks
Swedish Research Council (VR) (2019-05008), 2020-01-01 -- 2023-12-31.
Subject Categories
Communication Systems
Computer Systems
Other Electrical Engineering, Electronic Engineering, Information Engineering
DOI
10.1364/OFC.2024.M1H.1