Application of artificial intelligence methods to analyze human behavioral biometrics in ensuring the security of complex information systems

This article examines the application of artificial intelligence methods and technologies to analyzing human behavioral biometrics in the security of complex information systems. The relevance of the study stems from the limitations of traditional authentication mechanisms, which focus primarily on the initial stage of a user session and are ineffective in detecting user impersonation during interaction with the system. An alternative approach is proposed, using user behavioral characteristics to continuously assess trust in the current session. The paper analyzes anonymized text input data on a mobile device, reflecting the temporal and structural features of user interaction with the interface. It is shown that the combination of such characteristics allows for the identification of stable behavioral patterns suitable for user profiling. Using dimensionality reduction and cluster analysis methods, typical behavioral profiles are identified, differing in input style and rhythm, as well as the nature of corrections. Cluster membership is established to be maintained across multiple sessions with acceptable variability in individual characteristics. A risk-based approach to assessing behavioral deviations is proposed, based on comparing current behavioral indicators with a typical cluster profile. The study's results confirm the feasibility of using cluster behavioral profiles in risk-based access control systems and can be used in the design and development of continuous authentication mechanisms in complex information systems.

1. Kochegurova E.A., Zateev R.P. Hidden Monitoring Based on Keystroke Dynamics in Online Examination System. Programming and Computer Software. 2022;48(6):385–398. https://doi.org/10.1134/s0361768822060044

2. Yaacob M.N., Idrus S.Z.S., Ali W.N.A.W., et al. A Review on Feature Extraction in Keystroke Dynamics. Journal of Physics: Conference Series. 2020;1529(2). https://doi.org/10.1088/1742-6596/1529/2/022088

3. Smirnov I.S., Kochkarov A.A. The study of behavioral biometrics using data analysis and machine learning methods. Modeling, Optimization and Information Technology. 2024;12(2). (In Russ.). https://doi.org/10.26102/2310-6018/2024.45.2.021

4. Sağbaş E.A., Ballı S. Machine learning-based novel continuous authentication system using soft keyboard typing behavior and motion sensor data. Neural Computing & Applications. 2024;36(10):5433–5445. https://doi.org/10.1007/s00521-023-09360-9

5. Stragapede G., Delgado-Santos P., Tolosana R., et al. TypeFormer: transformers for mobile keystroke biometrics. Neural Computing & Applications. 2024;36:18531–18545. https://doi.org/10.1007/s00521-024-10140-2

6. Palin K., Feit A.M., Kim S., Kristensson P.O., Oulasvirta A. How do people type on mobile devices?: Observations from a study with 37,000 volunteers. In: MobileHCI '19: Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services, 01–04 October 2019, Taipei, Taiwan. New York: Association for Computing Machinery; 2019. https://doi.org/10.1145/3338286.3340120

7. Gautam N., Kumar N. Customer segmentation using k-means clustering for developing sustainable marketing strategies. Business Informatics. 2022;16(1):72–82. https://doi.org/10.17323/2587-814X.2022.1.72.82

8. Dias T., Vitorino J., Maia E., Sousa O., Praça I. KeyRecs: A keystroke dynamics and typing pattern recognition dataset. Data in Brief. 2023;50. https://doi.org/10.1016/j.dib.2023.109509

9. Wetherell M.A., Lau Sh.-H., Maxion R.A. The effect of socially evaluated multitasking stress on typing rhythms. Psychophysiology. 2023;60(8). https://doi.org/10.1111/psyp.14293

10. Tahir M., Halim Z., Waqas M., Sukhia K.N., Tu Sh. Emotion detection using convolutional neural network and long short-term memory: a deep multimodal framework. Multimedia Tools and Applications. 2023;83:53497–53530. https://doi.org/10.1007/s11042-023-17653-3

11. Lis K., Niewiadomska-Szynkiewicz E., Dziewulska K. Siamese Neural Network for Keystroke Dynamics-Based Authentication on Partial Passwords. Sensors. 2023;23(15). https://doi.org/10.3390/s23156685

12. Wahab A.A., Hou D., Schuckers S., Barbir A. Utilizing Keystroke Dynamics as Additional Security Measure to Protect Account Recovery Mechanism. In: Proceedings of the 7th International Conference on Information Systems Security and Privacy: Volume 1, 11–13 February 2021, Virtual Event. SciTePress; 2021. P. 33–42. https://doi.org/10.5220/0010191200330042