USER AUTHENTICATION IN INFORMATION SYSTEMS BASED ON BIOMETRIC SIGNALS OF MOBILE DEVICES

DOI: 10.31673/2409-7292.2025.041211

Abstract

The use of physiological biometric signals obtained using mobile devices to improve the efficiency and reliability of
authentication in information systems has been investigated. It has been established that dynamic parameters – heart rate (HR),
heart rate variability (HRV), blood oxygen saturation (SpO₂), skin temperature and respiratory rate – are capable of forming an
individual biometric user profile that can be used for continuous authentication. The results of biometric authentication using
mobile devices have been compared with classical methods based on fingerprints and face recognition, and their advantages
have been identified: dynamism, adaptability and increased resistance to spoofing attacks. A method for constructing a biometric
user matrix with periodic updates every 5 minutes has been proposed, which demonstrates stable authentication results and
confirms the feasibility of using such an approach even without the use of complex machine learning models. The impact of
changes in the user's physiological state (stress, physical activity, recovery period) on the stability of the authentication process
is analyzed, and the effectiveness of approaches that combine several types of biometric data to increase the reliability of
recognition is also investigated. Promising directions for integrating mobile devices with machine learning, blockchain, and
quantum-resistant encryption technologies are identified in order to create secure, adaptive, and energy-efficient identification
systems. It is shown that physiological signals of mobile devices are a key element of future continuous authentication systems
in information security.
Keywords: physiological biometric signals, mobile devices, authentication, blockchain, continuous authentication,
information security, information protection, user identification.

References
1. Manta, C., Jain, S. S., Coravos, A., Mendelsohn, D., & Izmailova, E. S. (2020). An Evaluation of Biometric
Monitoring Technologies for Vital Signs in the Era of COVID-19 // Clinical and Translational Science, 13(6), 1034–
1044. https://doi.org/10.1111/cts.12874.
2. Sun, W., Guo, Z., Yang, Z., Wu, Y., Lan, W., Liao, Y., Wu, X., & Liu, Y. (2022). A Review of Recent
Advances in Vital Signals Monitoring of Sports and Health via Flexible Wearable Sensors // Sensors, 22(20), 7784.
https://doi.org/10.3390/s22207784.
3. Chhibbar, L. D., Patni, S., Todi, S., Bhatia, A., & Tiwari, K. (2024). Enhancing security through continuous
biometric authentication using wearable sensors // Internet of Things, 28, 101374. https://doi.org/10.1016/j.iot.
2024.101374.
4. Shao, W., Liang, Z., Zhang, R., Fang, R., Miao, N., Kourkchi, E., Rafatirad, S., Homayoun, H., & Fang, C.
(2025). Know Me by My Pulse: Toward Practical Continuous Authentication on Wearable Devices via Wrist-Worn PPG
// arXiv preprint arXiv:2508.13690. https://doi.org/10.48550/arXiv.2508.13690.
5. Журавель Ю.І., Лісовський Б.В. (2025). Аналіз моделей та алгоритмів автентифікації на основі
біометричних даних. Сучасний захист інформації, №2(62), 51–58. https://doi.org/10.31673/2409-7292.2025.022701
6. O’Grady, B., Lambe, R., Baldwin, M., Acheson, T., & Doherty, C. (2024). The Validity of Apple Watch
Series 9 and Ultra 2 for Serial Measurements of Heart Rate Variability and Resting Heart Rate // Sensors, 24(19), 6220.
https://doi.org/10.3390/s24196220.
7. Bonneval, L., Wing, D., Sharp, S., Parra, M. T., Moran, R., LaCroix, A., & Godino, J. (2025). Validity of
Heart Rate Variability Measured with Apple Watch Series 6 Compared to Laboratory Measures // Sensors, 25(8), 2380.
https://doi.org/10.3390/s25082380.
8. Windisch, P., Schröder, C., Förster, R., Cihoric, N., & Zwahlen, D. R. (2023). Accuracy of the Apple Watch
Oxygen Saturation Measurement in Adults: A Systematic Review // Cureus, 15(2), e35355. https://doi.org/10.7759/
cureus.35355.
9. Browne, S. H., Bernstein, M., & Bickler, P. E. (2025). Evaluation of Pulse Oximetry Accuracy in a
Commercial Smartphone and Smartwatch Device During Human Hypoxia Laboratory Testing // Sensors, 25(5), 1286.
https://doi.org/10.3390/s25051286.
10. Alzueta, E., Gombert-Labedens, M., Javitz, H., Yuksel, D., Perez-Amparan, E., Camacho, L., Kiss, O.,
Zambotti, M., Sattari, N., Alejandro-Pena, A., Zhang, J., Shuster, A., Morehouse, A., Simon, K., Mednick, S., & Baker,
F. C. (2024). Menstrual Cycle Variations in Wearable-detected Finger Temperature and Heart Rate, but not in Sleep
Metrics, in Young and Midlife Individuals // Journal of Biological Rhythms, 39(5), 395–412. https://doi.org/10.1177/
07487304241265018.
11. Muratyan, A., Cheung, W., Dibbo, S. V., & Vhaduri, S. (2021). Opportunistic Multi-Modal User
Authentication for Health-Tracking IoT Wearables // arXiv preprint arXiv:2109.13705. https://doi.org/10.48550/
arXiv.2109.13705.
12. Sancho, J., Alesanco, Á., & García, J. (2018). Biometric Authentication Using the PPG: A Long-Term
Feasibility Study // Sensors, 18(5), 1525. https://doi.org/10.3390/s18051525.
13. Davoodi, M., Soker, A., Behar, J., & Yaniv, Y. (2023). Using Beat-to-Beat Heart Signals for AgeIndependent Biometric Verification // Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-42841-4.
14. Ashtiyani, M., Iavasani, S. N., Alvar, A. A., & Deevband, M. R. (2018). Heart Rate Variability Classification
Using Support Vector Machine and Genetic Algorithm // Journal of Biomedical Physics and Engineering, 8(4).
https://doi.org/10.31661/jbpe.v0i0.614.
15. Wittenberg, T., Koch, R., Pfeiffer, N., & Eskofier, B. (2020). Evaluation of HRV Estimation Algorithms
from PPG Data Using Neural Networks // Current Directions in Biomedical Engineering, 6(3), 505–509. https://doi.org/
10.1515/cdbme-2020-3130.
16. Ding, J., Liu, Q., Ling, B. W.-K., & Li, W. (2026). Heart Rate Estimation Based on Joint Convolutional
Neural Network and Conditional Generative Adversarial Network via Heart Rate Variabilities and Other Features
Extracted from Photoplethysmograms // Biomedical Signal Processing and Control, 112(C), 108831. https://doi.org/10.
1016/j.bspc.2025.108831.
17. Ólafsdóttir G. B., Larsson J. Deep Learning Approach for Extracting Heart Rate Variability from a
Photoplethysmographic Signal // Bachelor Thesis, Kristianstad University, Sweden. 2020. Режим доступу: https://
researchportal.hkr.se/ws/portalfiles/portal/35216086/FULLTEXT01.pdf.