1. SISN
  2. All Volumes and Issues
  3. Volume 15, 2024
  4. Realization of Reliable and Effective Authentication in Intelligent Systems by Using Visual Biometrics Methods

Realization of Reliable and Effective Authentication in Intelligent Systems by Using Visual Biometrics Methods

SISN.
2024;
Volume 15
: pp. 23 - 42
https://doi.org/10.23939/sisn2024.15.023
Authors:
  1. Taras Batiuk
  2. Dmytro Dosyn
1
Lviv Polytechnic National University, Ukraine
2
Lviv Polytechnic National University

The main purpose of this article is to consider the aspects of ensuring security and increasing the efficiency of the authentication process in intelligent systems using visual biometrics. The work is aimed at the development and improvement of authentication systems using advanced biometric identification methods. An intelligent system has been created that ensures secure authentication of users of the current system, using a Siamese neural network. In addition to the implementation of basic security measures in the form of hashing and saving user logins and passwords, the implementation of two-factor authentication is important nowadays, which significantly strengthens the protection of user data and prevents most modern methods of hacking and stealing user data. Two-factor authentication is implemented as a technology for searching, recognizing and comparing the faces of system users, as visual biometrics is more secure than other types of two-factor authentication. Different variations of the possible implementation of Siamese neural network using Contrastive loss function and more modern Triplet loss function were reviewed and accordingly, a neural network using Triplet loss function was accomplished and trained. After training and verifying the correct operation of the neural network, it was integrated into the created intelligent system, thanks to which an effective way of recognizing the face of the system user was created, saving the received information in the database and further comparing the current user with the stored face during authentication. As a result, a secure and reliable intelligent system was created that cutting down the risk of unapproved access to the user account and uses an effective and modern method of user authentication.

two-factor authentication
Siamese neural network
Triplet Loss Function
visual biometrics
facial recognition technologies
  1. Long, X., Zhuang, W., Xia, M., Hu, K., & Lin, H. (2024). SASiamNet: Self-adaptive Siamese Network for change detection of remote sensing image. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 1021–1034. DOI: https://doi.org/10.1109/jstars.2023.3330753
  2. Ning, M., Tang, J., Zhong, H., Wu, H., Zhang, P., & Zhang, Z. (2022). Scale-Aware Network with Scale Equivariance. Photonics, 9(3), 142–142. DOI: https://doi.org/10.3390/photonics9030142
  3. Batiuk, T., & Dosyn, D. (2023). Intellectual system for clustering users of social networks derived from the message sentiment analysis. Journal of Lviv Polytechnic National University “Information Systems and Networks”, 13, 121–138. DOI: https://doi.org/10.23939/sisn2023.13.121
  4. Zhao, Y., Song, X., Li, J., & Liu, Y. (2024). CSCNet: A Cross-Scale Coordination Siamese Network for Building Change Detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 1377–1389. DOI: https://doi.org/10.1109/jstars.2023.3337999
  5. Farabbi, A., & Mainardi, L. (2023). Domain-Specific Processing Stage for Estimating Single-Trail Evoked Potential Improves CNN Performance in Detecting Error Potential. Sensors, 23(22), 9049–9049. DOI: https://doi.org/10.3390/s23229049
  6. Cheng, L., Zheng, X., Zhao, M., Dou, R., Yu, S., Wu, N., & Liu, L. (2022). SiamMixer: A Lightweight and Hardware-Friendly Visual Object-Tracking Network. Sensors, 22(4), 1585–1585. DOI: https://doi.org/10.3390/s22041585
  7. Kummerow, A., Monsalve, C., & Bretschneider, P. (2021). Siamese recurrent neural networks for the robust classification of grid disturbances in transmission power systems considering unknown events. IET Smart Grid, 5(1), 51–61. DOI: https://doi.org/10.1049/stg2.12051
  8. Batiuk T., Vysotska V., Lytvyn V. (2020). Intellectual System for Socialization by Personal Interests on the Basis of SEO Algorithms and Techniques of Machine Learning. CEUR Workshop Proceedings, 4th Intern. Conf. on Computational Linguistics and Intellectual Systems, COLINS 2020, 23–24 April 2020, Lviv, Ukraine, 2604, 1237– 1250.
  9. Gao, Y., Wu, H., Liao, H., Chen, X., Yang, S., & Han, X. (2023). A fault diagnosis method for rolling bearings based on graph neural network with one-shot learning. EURASIP Journal on Advances in Signal Processing, 2023(1). DOI: https://doi.org/10.1186/s13634-023-01063-6
  10. Mo, W., Tan, Y., Zhang, Y., Zhi, Y., Cai, Y., & Ma, W. (2023). Multispectral Remote Sensing Image Change Detection Based on Twin Neural Networks. Electronics, 12(18), 3766–3766. DOI: https://doi.org/10.3390/electronics12183766
  11. Batiuk, T., & Vysotska, V. (2022). Technology for personalities socialization by common interests derived from machine learning techniques and seo-algorithms. Radio Electronics, Computer Science, Control, 2, 53. DOI: https://doi.org/10.15588/1607-3274-2022-2-6
  12. Pang, H., Xie, M., Liu, C., Ma, R., & Han, L. (2021). Siamese tracking combing frequency channel attention with adaptive template. IET Communications, 15(20), 2493–2502. DOI: https://doi.org/10.1049/cmu2.12280
  13. Basu, T., Menzer, O., Ward, J., & SenGupta, I. (2022). A Novel Implementation of Siamese Type Neural Networks in Predicting Rare Fluctuations in Financial Time Series. Risks, 10(2), 39. DOI: https://doi.org/10.3390/risks10020039
  14. Yuan, D., Li, Q., Yang, X., Zhang, M., & Sun, Z. (2022). Object-Aware Adaptive Convolution Kernel Attention Mechanism in Siamese Network for Visual Tracking. Applied Sciences, 12(2), 716. DOI: https://doi.org/10.3390/app12020716
  15. Lee, D., & Jeong, J. (2023). Few-Shot Learning-Based Light-Weight WDCNN Model for Bearing Fault Diagnosis in Siamese Network. Sensors, 23(14), 6587–6587. DOI: https://doi.org/10.3390/s23146587
  16. Batiuk T., Vysotska V., Holoshchuk R., Holoshchuk S. (2022). Intellectual System for Socialization of Individual’s with Contributed Interests derived from NLP, Machine Learning and SEO Algorithms. CEUR Workshop Proceedings, 6th Intern. Conf. on Computational Linguistics and Intellectual Systems, COLINS 2022, 12–13 May 2022, Gliwice, Poland, 3171, 572–631.
  17. Ahmed, S., Lee, K. H., & Jung, H. Y. (2022). Robust Hippocampus Localization From Structured Magnetic Resonance Imaging Using Similarity Metric Learning. IEEE Access, 10,  7141–7152. DOI: https://doi.org/10.1109/access.2021.3137824
  18. Islem Jarraya, F. Saïd, Hamdani, T. M., Bilel Neji, & Alimi, A. M. (2022). Biometric-Based Security System for Smart Riding Clubs. IEEE Access, 10, 132012–132030. DOI: https://doi.org/10.1109/access.2022.3229260
  19. Song, C., & Ji, S. (2022). Face Recognition Method Based on Siamese Networks Under Non-Restricted Conditions. IEEE Access, 10, 40432–40444. DOI: https://doi.org/10.1109/access.2022.3167143