Experimental Analysis of Adaptive ML Classifiers for Dynamic Detection of Emerging Physical-Layer Attacks
Paper in proceeding, 2025
We experimentally evaluate three ML classifiers for detecting physical-layer attacks in optical networks. Using telemetry data from a real-world testbed under six attack types, we achieve Balanced Accuracy of up to 0.936 for unseen attacks, and demonstrate rapid adaptation of Multilayer Perceptron to evolving threats.
data stream
machine learning
attack detection
Author
Aleksandra Knapinska
Wrocław University of Science and Technology
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
Marija Furdek Prekratic
Chalmers, Electrical Engineering, Communication, Antennas and Optical Networks
European Conference on Optical Communication, ECOC
9798331595319 (ISBN)
51st European Conference on Optical Communication (ECOC 2025)
Copenhagen, Denmark,
Copenhagen, Denmark,
5G Trusted And seCure network servICes (5G-TACTIC)
European Commission (EC) (EC/H2020/101127973), 2023-12-01 -- 2026-11-30.
Areas of Advance
Information and Communication Technology
Subject Categories (SSIF 2025)
Communication Systems
Computer Sciences
Computer Systems
DOI
10.1109/ECOC66593.2025.11263047
ISBN
9798331595319