Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring
We present a thorough machine-learning framework based on real-time state-of-polarization (SOP) monitoring for robust anomaly identification in optical fiber networks. We exploit SOP data under three different threat scenarios: (i) malicious or critical vibration events, (ii) overlapping mechanical...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/6/7/131 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850067522197389312 |
|---|---|
| author | Gulmina Malik Imran Chowdhury Dipto Muhammad Umar Masood Mashboob Cheruvakkadu Mohamed Stefano Straullu Sai Kishore Bhyri Gabriele Maria Galimberti Antonio Napoli João Pedro Walid Wakim Vittorio Curri |
| author_facet | Gulmina Malik Imran Chowdhury Dipto Muhammad Umar Masood Mashboob Cheruvakkadu Mohamed Stefano Straullu Sai Kishore Bhyri Gabriele Maria Galimberti Antonio Napoli João Pedro Walid Wakim Vittorio Curri |
| author_sort | Gulmina Malik |
| collection | DOAJ |
| description | We present a thorough machine-learning framework based on real-time state-of-polarization (SOP) monitoring for robust anomaly identification in optical fiber networks. We exploit SOP data under three different threat scenarios: (i) malicious or critical vibration events, (ii) overlapping mechanical disturbances, and (iii) malicious fiber tapping (eavesdropping). We used various supervised machine learning techniques like k-Nearest Neighbor (k-NN), random forest, extreme gradient boosting (XGBoost), and decision trees to classify different vibration events. We also assessed the framework’s resilience to background interference by superimposing sinusoidal noise at different frequencies and examining its effects on the polarization signatures. This analysis provides insight into how subsurface installations, subject to ambient vibrations, affect detection fidelity. This highlights the sensitivity to which external interference affects polarization fingerprints. Crucially, it demonstrates the system’s capacity to discern and alert on malicious vibration events even in the presence of environmental noise. However, we focus on the necessity of noise-mitigation techniques in real-world implementations while providing a potent, real-time mechanism for multi-threat recognition in the fiber networks. |
| format | Article |
| id | doaj-art-68e1cafa05de437b985fa078c2a15670 |
| institution | DOAJ |
| issn | 2673-2688 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj-art-68e1cafa05de437b985fa078c2a156702025-08-20T02:48:17ZengMDPI AGAI2673-26882025-06-016713110.3390/ai6070131Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization MonitoringGulmina Malik0Imran Chowdhury Dipto1Muhammad Umar Masood2Mashboob Cheruvakkadu Mohamed3Stefano Straullu4Sai Kishore Bhyri5Gabriele Maria Galimberti6Antonio Napoli7João Pedro8Walid Wakim9Vittorio Curri10Department of Electronics and Telecommunications, Polytechnic University of Turin, 10129 Turin, ItalyDepartment of Electronics and Telecommunications, Polytechnic University of Turin, 10129 Turin, ItalyDepartment of Electronics and Telecommunications, Polytechnic University of Turin, 10129 Turin, ItalyDepartment of Electronics and Telecommunications, Polytechnic University of Turin, 10129 Turin, ItalyLINKS Foundation, 10129 Turin, ItalyOptical Networks, Nokia, Bangalore 560045, IndiaOptical Networks, Nokia, 20060 Milan, ItalyOptical Networks, Nokia, 81541 Munich, GermanyOptical Networks, Nokia, 2720-092 Carnaxide, PortugalOptical Networks, Nokia, Naperville, IL 60563, USADepartment of Electronics and Telecommunications, Polytechnic University of Turin, 10129 Turin, ItalyWe present a thorough machine-learning framework based on real-time state-of-polarization (SOP) monitoring for robust anomaly identification in optical fiber networks. We exploit SOP data under three different threat scenarios: (i) malicious or critical vibration events, (ii) overlapping mechanical disturbances, and (iii) malicious fiber tapping (eavesdropping). We used various supervised machine learning techniques like k-Nearest Neighbor (k-NN), random forest, extreme gradient boosting (XGBoost), and decision trees to classify different vibration events. We also assessed the framework’s resilience to background interference by superimposing sinusoidal noise at different frequencies and examining its effects on the polarization signatures. This analysis provides insight into how subsurface installations, subject to ambient vibrations, affect detection fidelity. This highlights the sensitivity to which external interference affects polarization fingerprints. Crucially, it demonstrates the system’s capacity to discern and alert on malicious vibration events even in the presence of environmental noise. However, we focus on the necessity of noise-mitigation techniques in real-world implementations while providing a potent, real-time mechanism for multi-threat recognition in the fiber networks.https://www.mdpi.com/2673-2688/6/7/131state of polarizationmachine learningrandom forestXGBoostdecision treek-NN |
| spellingShingle | Gulmina Malik Imran Chowdhury Dipto Muhammad Umar Masood Mashboob Cheruvakkadu Mohamed Stefano Straullu Sai Kishore Bhyri Gabriele Maria Galimberti Antonio Napoli João Pedro Walid Wakim Vittorio Curri Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring AI state of polarization machine learning random forest XGBoost decision tree k-NN |
| title | Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring |
| title_full | Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring |
| title_fullStr | Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring |
| title_full_unstemmed | Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring |
| title_short | Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring |
| title_sort | resilient anomaly detection in fiber optic networks a machine learning framework for multi threat identification using state of polarization monitoring |
| topic | state of polarization machine learning random forest XGBoost decision tree k-NN |
| url | https://www.mdpi.com/2673-2688/6/7/131 |
| work_keys_str_mv | AT gulminamalik resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT imranchowdhurydipto resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT muhammadumarmasood resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT mashboobcheruvakkadumohamed resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT stefanostraullu resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT saikishorebhyri resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT gabrielemariagalimberti resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT antonionapoli resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT joaopedro resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT walidwakim resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring AT vittoriocurri resilientanomalydetectioninfiberopticnetworksamachinelearningframeworkformultithreatidentificationusingstateofpolarizationmonitoring |