Security detection method of illegal intrusion in optical transmission sensor networks based on a dual-path refinement attention mechanism

• Autorzy: Lin Mi , Zhang Huanyu , Liu Xiaomin , Zhang Yu , Hong Jie

Identyfikatory

DOI

10.24425/opelre.2025.156669

• Języki publikacji: EN

Abstrakty

EN

This paper proposes a security detection method based on a dual-path refined attention mechanism to address the complex and variable illegal intrusion behaviours and low detection efficiency in optical transmission sensor networks. By constructing a multi-scale convolutional attention module, efficient fusion of local and global features can be achieved, combining ResNet50 structure optimisation with XGBoost classifier to improve the model ability to discriminate intrusion features and detection speed. The experimental results demonstrate that this method outperforms existing methods in terms of detection rate, real-time performance, and anti-interference capability, particularly in maintaining low network overhead under high attack densities. This study provides a reliable intrusion detection solution for optical transmission sensor networks, which is of great value in enhancing security protection capabilities in complex network environments.

Słowa kluczowe

EN

dual-path attention mechanism; optical transmission sensor network; trespassing; safety testing; convolutional attention module

• Wydawca: Stowarzyszenie Elektryków Polskich ; Polska Akademia Nauk ; Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Opto-Electronics Review
• Rocznik: 2025
• Tom: Vol. 33, No. 4
• Strony: art. no. e156669
• Opis fizyczny: Bibliogr. 20 poz., rys., wykr., tab.

Twórcy

autor

Lin Mi

• Power Dispatching Control Center, Hainan Power Grid Co., Ltd., Haikou 570203, China

autor

Zhang Huanyu

• Power Dispatching Control Center, Hainan Power Grid Co., Ltd., Haikou 570203, China

autor

Liu Xiaomin

• Power Dispatching Control Center, Hainan Power Grid Co., Ltd., Haikou 570203, China

autor

Zhang Yu

• Power Dispatching Control Center, Hainan Power Grid Co., Ltd., Haikou 570203, China

autor

Hong Jie

• Power Dispatching Control Center, Hainan Power Grid Co., Ltd., Haikou 570203, China

Bibliografia

• [1] Reyes-Vera, E. et al. Machine learning applications in optical fiber sensing: A research agenda. Sensors 24, 2200 (2024). https://doi.org/10.3390/s24072200
• [2] Jin, S. B. & Zhang, L. Detection of false data injection attack in internet of things based on Bayesian. Comput. Simul. 39, 406–410 (2022). https://doi.org/10.3969/j.issn.1006-9348.2022.11.080 (in Chinese)
• [3] Wang, Y., Bao, Q., Wang, J., Su, G. & Xu, X. Cloud computing for large-scale resource computation and storage in machine learning. J. Theory Pract. Eng. Sci. 4, 163–171 (2024). https://doi.org/10.53469/jtpes.2024.04(03).14
• [4] Kumar, N., Kasbekar, G. S., & Manjunath, D. Application of data collected by endpoint detection and response systems for implementation of a network security system based on zero trust principles and the Eigen Trust algorithm. Perform. Eval. Rev. 50, 5–7 (2023). https://doi.org/10.48550/arXiv.2203.09325
• [5] Jing, W. & Zhang, J. Wireless sensor network intrusion detection algorithm based on blockchain technology. Chin. J. Sensor. Actuator. 36, 978–983 (2023). https://doi.org/10.3969/j.issn.1004-1699.2023.06.019 (in Chinese)
• [6] Liu, Y. M., Yang, Y. J., Luo, H. Y., Huang, H. & Xie, T. Q. Intrusion detection method for wireless sensor network based on bidirectional circulation generative adversarial network. J. Comput. Appl. 43, 160–168 (2023). https://www.joca.cn/CN/10.11772/j.issn.1001-9081.2021112001 (in Chinese)
• [7] Wang, X. Y., Xing, H. Y., Hou, T. H. & Zheng, J. C. Research on wireless sensor network intrusion detection based on evolutionary game. J. Electron. Meas. Instrum. 37, 97–105 (2023). https://doi.org/10.13382/j.jemi.B2306568 (in Chinese)
• [8] Karthic, S. & Kumar, S. M. Hybrid optimized deep neural network with enhanced conditional random field based intrusion detection on wireless sensor network. Neural Process. Lett. 55, 459–479 (2023). https://doi.org/10.1007/s11063-022-10892-9
• [9] Chang, J. et al. Multi-scale attention network for building extraction from high-resolution remote sensing images. Sensors 24, 1010 (2024). https://doi.org/10.3390/s24031010
• [10] Mady, A., Gupta, S. & Warkentin, M. The effects of knowledge mechanisms on employees' information security threat construal. Inf. Syst. J. 33, 790–841 (2023). https://doi.org/10.1111/isj.12424
• [11] Yin, Z. et al. Deep CSI compression for massive MIMO: A self-information model-driven neural network. IEEE Trans. Wirel. Commun. 21, 8872–8886 (2022). https://doi.org/10.1109/TWC.2022.3170576
• [12] Mohy-Eddine, M., Guezzaz, A., Benkirane, S., Azrour, M. & Farhaoui, Y. An ensemble learning based intrusion detection model for industrial IoT security. Big Data Min. Anal. 6, 273–287 (2023). https://doi.org/10.26599/BDMA.2022.9020032
• [13] Rajalakshmi, R., Sivakumar, P., Prathiba, T. & Chatrapathy, K. An energy efficient deep learning model for intrusion detection in smart healthcare with optimal feature selection mechanism. J. Intell. Fuzzy Syst .44, 2753–2768 (2023). https://doi.org/10.3233/JIFS-223166
• [14] Nayak, K. V., Arunalatha, J. S., Vasanthakumar, G. U. & Venugopal, K. R. Design of deep convolution feature extraction for multimedia information retrieval. Int. J. Intell. Unmanned Syst. 11, 5–19 (2023). https://doi.org/10.1108/IJIUS-11-2021-0126
• [15] Wang, S., Lin, S. & Yang, R. A lightweight convolutional neural network for multipoint displacement measurements on bridge structures. Nonlinear Dyn. 112, 11745–11763 (2024). https://doi.org/10.1007/s11071-024-09673-x
• [16] Majidian, Z., TaghipourEivazi, S., Arasteh, B. & Babai, S. An intrusion detection method to detect denial of service attacks using error-correcting output codes and adaptive neuro-fuzzy inference. Comput. Electr. Eng. 106, 108600 (2023). https://doi.org/10.1016/j.compeleceng.2023.108600
• [17] Guo, Z. Criminalisation of the illegal use of personal data: comparative approaches and the Chinese choice. Humanit. Soc. Sci. Commun. 12, 782 (2025). https://doi.org/10.1057/s41599-025-05141-y
• [18] Vladov, S. et al. Neural network method of analysing sensor data to prevent illegal cyberattacks. Sensors 25, 5235 (2025). https://doi.org/10.3390/s25175235
• [19] Choudhury, A., Mondal, A. & Sarkar, S. Searches for the BSM scenarios at the LHC using decision tree-based machine learning algorithms: a comparative study and review of random forest, AdaBoost, XGBoost and LightGBM frameworks. Eur. Phys. J. Spec. Top. 233, 2425–2463 (2024). https://doi.org/10.1140/epjs/s11734-024-01308-x
• [20] Attou, H., Guezzaz, A., Benkirane, S., Azrour, M. & Farhaoui, Y. Cloud-based intrusion detection approach using machine learning techniques. Big Data Min. Anal. 6, 311–320 (2023). https://doi.org/10.26599/BDMA.2022.9020038