Fiber-optic network infrastructures are crucial for the transmission of data over long and short distances. Fiber optics are also preferred for the infrastructure of in-building data communications. In this study, we use polarization analysis to ensure the security of the optical fiber/cables of the physical layer. This method exploits the changes induced by mechanical vibrations to polarization states, which can be easily detected using a polarization beam splitter and a balancing photodetector. We use machine learning to classify selected events that violate the safety of the physical layer, such as manipulation or temporary disconnection of connectors. The results show the resting state can be accurately distinguished from selected security breaches for a fiber route subjected to environmental disturbances, where individual events can be classified with nearly 99% accuracy.

Department of Telecommunications Faculty of Electrical Engineering and Communications Brno University of Technology Technicka 12 616 00 Brno Czech Republic

Zobrazit více v PubMed

Dejdar P., Hanak P., Munster P., Horvath T. Polarization Monitor for High-speed State of Polarization Changes Detection. Int. J. Adv. Telecommun. Electrotech. Signals Syst. 2021;10:13–17. doi: 10.11601/ijates.v10i1-3.296. DOI

Li J., Zhou X., Zhang M., Zhang J., Qiao L., Zhao L., Yin Z. Temperature Resolution Improvement in Raman-Based Fiber-Optic Distributed Sensor Using Dynamic Difference Attenuation Recognition. Sensors. 2020;20:6922. doi: 10.3390/s20236922. PubMed DOI PMC

Dejdar P., Záviška P., Valach S., Münster P., Horváth T. Image Edge Detection Methods in Perimeter Security Systems Using Distributed Fiber Optical Sensing. Sensors. 2022;22:4573. doi: 10.3390/s22124573. PubMed DOI PMC

Ershov I.A., Stukach O.V. Choice of Wavelet for Filtering of Signal from Fiber-Optic Temperature Sensor; Proceedings of the 2022 Moscow Workshop on Electronic and Networking Technologies (MWENT); Moscow, Russia. 9–11 June 2022; pp. 1–4. DOI

Zhou R., Gao H., Feng Z., Qiao X. Simulation and hardware implementation of demodulation for fiber optic seismic sensor with linear edge filtering method. Opt. Fiber Technol. 2020;60:102384. doi: 10.1016/j.yofte.2020.102384. DOI

Lou K., Peng C.Y., Tang W.S., Hu Z.L., Xu P., Tie X. Application of Acoustic Horns for the Amplification of Fiber Optic Vector Hydrophone Signal; Proceedings of the 2021 4th International Conference on Information Communication and Signal Processing (ICICSP); Shenzhen, China. 26–28 November 2021; pp. 139–142. DOI

Spurny V., Munster P., Tomasov A., Horvath T., Skaljo E. Physical layer components security risks in optical fiber infrastructures. Sensors. 2022;22:588. doi: 10.3390/s22020588. PubMed DOI PMC

Liu F., Zhang H., Li X., Li Z., Wang H. Intrusion identification using GMM-HMM for perimeter monitoring based on ultra-weak FBG arrays. Opt. Express. 2022;30:17307–17320. doi: 10.1364/OE.452418. PubMed DOI

Wang M., Sun Z., Zhang F., Min L., Li S., Jiang S. Application Research of FBG Vibration Sensor Used for Perimeter Security; Proceedings of the 2018 IEEE 3rd Optoelectronics Global Conference (OGC); Shenzhen, China. 4–7 September 2018; pp. 94–97. DOI

Cai Y., Yan W., Liu H., Sun Y., Zhou X. Security monitoring of smart campus using distributed fiber optic acoustic sensing. In: Zhang J., Fu S., Zhang H., editors. Proceedings of the AOPC 2020: Optical Information and Network. Volume 11569. International Society for Optics and Photonics, SPIE; Bellingham, WA, USA: 2020. p. 115690L. DOI

Duckworth G.L., Ku E.M. OptaSense distributed acoustic and seismic sensing using COTS fiber optic cables for infrastructure protection and counter terrorism. In: Carapezza E.M., editor. Proceedings of the Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense XII. Volume 8711. International Society for Optics and Photonics, SPIE; Bellingham, WA, USA: 2013. p. 87110G. DOI

Kishida K., Imai M., Kawabata J., Guzik A. Distributed Optical Fiber Sensors for Monitoring of Civil Engineering Structures. Sensors. 2022;22:4368. doi: 10.3390/s22124368. PubMed DOI PMC

Stepanov K.V., Zhirnov A.A., Sazonkin S.G., Pnev A.B., Bobrov A.N., Yagodnikov D.A. Non-Invasive Acoustic Monitoring of Gas Turbine Units by Fiber Optic Sensors. Sensors. 2022;22:4781. doi: 10.3390/s22134781. PubMed DOI PMC

Shi J., Cui K., Wang H., Ren Z., Zhu R. An Interferometric Optical Fiber Perimeter Security System Based on Multi-Domain Feature Fusion and SVM. IEEE Sens. J. 2021;21:9194–9202. doi: 10.1109/JSEN.2021.3055346. DOI

Gu X., Wang T., Hou S., Peng J., Wang H., Xia Q. Multi-Feature-Based Intrusion Detection for Optical Fiber Perimeter Security System: A Aase Study; Proceedings of the 2018 IEEE 17th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC); Berkeley, CA, USA. 16–18 July 2018; pp. 448–453. DOI

Wang N., Fang N., Wang L. Intrusion recognition method based on echo state network for optical fiber perimeter security systems. Opt. Commun. 2019;451:301–306. doi: 10.1016/j.optcom.2019.06.058. DOI

Yin S., Ruffin P.B., Yu F.T.S. Fiber Optic Sensors. 2nd ed. CRC Press; Boca Raton, FL, USA: 2017. pp. 1–477. Cited By:11.

Munster P., Horvath T., Vojtech J. Distributed Sensing Based on Interferometry and Polarization Methods for Use in Fibre Infrastructure Protection. Sensors. 2019;19:1810. doi: 10.3390/s19081810. PubMed DOI PMC

Yablochkin K.A., Dashkov M.V., Dashkov V.M. Investigation of the vibration influences on the optical fiber polarization characteristics. In: Andreev V.A., Bourdine A.V., Burdin V.A., Morozov O.G., Sultanov A.H., editors. Proceedings of the Optical Technologies for Telecommunications 2018. Volume 11146. International Society for Optics and Photonics, SPIE; Bellingham, WA, USA: 2019. p. 111461P. DOI

Šlapák M., Vojtěch J., Havliš O., Slavík R. Monitoring of Fibre Optic Links With a Machine Learning-Assisted Low-Cost Polarimeter. IEEE Access. 2020;8:183965–183971. doi: 10.1109/ACCESS.2020.3009524. DOI

Munster P., Horvath T., Sysel P., Vojtech J., Velc R. Comparison of interferometry based and polarization based sensing systems for use in fiber infrastructure protection; Proceedings of the 2017 International Workshop on Fiber Optics in Access Network (FOAN); Sarajevo, Bosnia and Herzegovina. 6–8 November 2017; pp. 1–3. DOI

Wada A., Tanaka S., Takahashi N. Simultaneous measurement of vibration and temperature using a Fabry-Perot interferometer in polarization maintaining fiber and laser diodes. In: Chung Y., Jin W., Lee B., Canning J., Nakamura K., Yuan L., editors. Proceedings of the 25th International Conference on Optical Fiber Sensors. Volume 10323. International Society for Optics and Photonics, SPIE; Bellingham, WA, USA: 2017. p. 1032326. DOI

Wang X., Hu J., Wang F., Yong Y., Zhang Y., Xue M., Zhang X., Pan S. Multi-vibration detection by probe pulses with ergodic SOPs in a POTDR system. Opt. Express. 2018;26:28349–28362. doi: 10.1364/OE.26.028349. PubMed DOI

Shaneman K., Gray S. Optical network security: Technical analysis of fiber tapping mechanisms and methods for detection & prevention; Proceedings of the IEEE MILCOM 2004. Military Communications Conference; Monterey, CA, USA. 31 October–3 November 2004; pp. 711–716. DOI

Skorin-Kapov N., Furdek M., Zsigmond S., Wosinska L. Physical-layer security in evolving optical networks. IEEE Commun. Mag. 2016;54:110–117. doi: 10.1109/MCOM.2016.7537185. DOI

Song H., Li Y., Liu M., Wang K., Li J., Zhang M., Zhao Y., Zhang J. Experimental study of machine-learning-based detection and location of eavesdropping in end-to-end optical fiber communications. Opt. Fiber Technol. 2022;68:102669. doi: 10.1016/j.yofte.2021.102669. DOI

Abdelli K., Cho J.Y., Azendorf F., Griesser H., Tropschug C., Pachnicke S. Machine-learning-based anomaly detection in optical fiber monitoring. J. Opt. Commun. Netw. 2022;14:365–375. doi: 10.1364/JOCN.451289. DOI

Liu M., Li Y., Song H., Tu Z., Zhao Y., Zhang J. Experimental Demonstration of Optical Fiber Eavesdropping Detection Based on Deep Learning; Proceedings of the Asia Communications and Photonics Conference; Chengdu, China. 2–5 November 2019; Washington, DC, USA: Optical Society of America; 2019. p. T1H-4.

Tomasov A., Dejdar P., Horvath T., Munster P. Physical fiber security by the state of polarization change detection. In: Lieberman R.A., Sanders G.A., Scheel I.U., editors. Proceedings of the Fiber Optic Sensors and Applications XVIII. Volume 12105. International Society for Optics and Photonics, SPIE; Orlando, FL, USA: 2022. p. 1210507. DOI

Kumar A., Ghatak A. Polarization of Light with Applications in Optical Fibers. SPIE; Bellingham, WA, USA: 2011. Basic Concepts of Polarization; pp. 19–46. DOI

Kumar A., Ghatak A. Polarization of Light with Applications in Optical Fibers. SPIE; Bellingham, WA, USA: 2011. Jones Vector Representation of Polarized Light; pp. 75–97. DOI

Kumar A., Ghatak A. Polarization of Light with Applications in Optical Fibers. SPIE; Bellingham, WA, USA: 2011. The Stokes Parameters Representation; pp. 97–120. DOI

Padgett M.J., Courtial J. Poincaré-sphere equivalent for light beams containing orbital angular momentum. Opt. Lett. 1999;24:430–432. doi: 10.1364/OL.24.000430. PubMed DOI

Dejdar P., Tomasov A., Munster P., Horvath T. Vibration caused by train detection using state-of-polarization changes measurement. In: Lieberman R.A., Sanders G.A., Scheel I.U., editors. Proceedings of the Fiber Optic Sensors and Applications XVIII. Volume 12105. International Society for Optics and Photonics, SPIE; Bellingham, WA, USA: 2022. p. 1210506. DOI

Xiao L., Wang Y., Li Y., Bai Q., Liu X., Jin B. Polarization Fading Suppression for Optical Fiber Sensing: A Review. IEEE Sens. J. 2022;22:8295–8312. doi: 10.1109/JSEN.2022.3161075. DOI

Paszke A., Gross S., Massa F., Lerer A., Bradbury J., Chanan G., Killeen T., Lin Z., Gimelshein N., Antiga L., et al. Advances in Neural Information Processing Systems 32. Curran Associates, Inc.; Red Hook, NY, USA: 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library; pp. 8024–8035.

Semenov A., Boginski V., Pasiliao E.L. Proceedings of the International Conference on Computational Data and Social Networks. Springer; Berlin/Heidelberg, Germany: 2019. Neural Networks with Multidimensional Cross-Entropy Loss Functions; pp. 57–62.

Phan T.H., Yamamoto K. Resolving class imbalance in object detection with weighted cross entropy losses. arXiv. 20202006.01413

Kingma D.P., Ba J. Adam: A method for stochastic optimization. arXiv. 20141412.6980