The mathematical model of keystroke dynamics biometric reference

This paper presents a mathematical model of a biometric reference template for keystroke dynamics, enabling biometric user identification based on free-text input. A review of contemporary scientific literature on the topic revealed that biometric reference templates can be represented using various features, such as typing speed, keystroke latency (time between keystrokes), or digraph (bigram) duration. It was identified that the primary feature enabling biometric identification is the time interval between consecutive keystrokes of character pairs (bigrams). The biometric reference template for keystroke dynamics is defined as a set of continuous probabilistic characteristics, each representing the distribution of time latencies between the keystrokes of specific character pairs. The model was evaluated for compliance with GOST (Russian State Standard) requirements. Its robustness to text variability was demonstrated, and integration efficiency was shown through lower memory usage compared to existing solutions. The possibility of using the model within a signal processing subsystem in a general-purpose biometric system architecture is described. The research results can be applied in the development of biometric identification systems compliant with GOST standards.

1. Artyushina L.A., Troitskaya E.A. Some Approaches to Assessing the Informative of User Identification Parameters by Keyboard Handwriting Based on Behavioral Biometrics. Bulletin of the South Ural State University. Series "Computer Technology, Automatic Control, Radio Electronics". 2022;22(3):30–38. (In Russ.). https://doi.org/10.14529/ctcr220303

2. Chekmarev D.Yu., Borzenkova S.Yu. Evaluation and Comparative Analysis of the Efficiency of Keyboard Handwriting Recognition Systems. News of the Tula State University. Technical Sciences. 2023;(12):490–492. (In Russ.).

3. Dimaratos A., Pöhn D. Evaluation Scheme to Analyze Keystroke Dynamics Methods. In: Proceedings of the 9th International Conference on Information Systems Security and Privacy, ICISSP 2023: Volume 1, 22–24 February 2023, Lisbon, Portugal. SciTePress; 2023. P. 357–365. https://doi.org/10.5220/0011626100003405

4. Kaluarachchi N., Kandanaarachchi S., Moore K., Arakala A. DEFT: A New Distance-Based Feature Set for Keystroke Dynamics. arXiv. URL: https://arxiv.org/abs/2310.04059 [Accessed 12th August 2025].

5. Roy S., Pradhan J., Kumar A., et al. A Systematic Literature Review on Latest Keystroke Dynamics Based Models. IEEE Access. 2022;10:92192–92236. https://doi.org/10.1109/ACCESS.2022.3197756

6. Smeaton A.F., Krishnamurthy N.G., Suryanarayana A.H. Keystroke Dynamics as Part of Lifelogging. In: MultiMedia Modeling: 27th International Conference, MMM 2021: Proceedings: Part II, 22–24 June 2021, Prague, Czech Republic. Cham: Springer; 2021. P. 183–195. https://doi.org/10.1007/978-3-030-67835-7_16

7. Unni S., Gowda S.S., Smeaton A.F. An Investigation into Keystroke Dynamics and Heart Rate Variability as Indicators of Stress. In: MultiMedia Modeling: 28th International Conference, MMM 2022: Proceedings: Part I, 06–10 June 2022, Phu Quoc, Vietnam. Cham: Springer; 2022. P. 379–391. https://doi.org/10.1007/978-3-030-98358-1_30

8. Ismail M.G., Salem M.A., Abd El Ghany M.A., Aldakheel E.A., Abbas S. Outlier Detection for Keystroke Biometric User Authentication. PeerJ Computer Science. 2024;10. https://doi.org/10.7717/peerj-cs.2086

9. Saitov I.A., Saitov A.I., Sharapov M.M. Authentication of a Critical Object Workstation Operator Based on Computer Handwriting. Journal of Instrument Engineering. 2023;66(6):449–456. (In Russ.). https://doi.org/10.17586/0021-3454-2023-66-6-449-456

10. Shadman R., Wahab A.A., Manno M., Lukaszewski M., Hou D., Hussain F. Keystroke Dynamics: Concepts, Techniques, and Applications. ACM Computing Surveys. 2025;57(11). https://doi.org/10.1145/3733103

11. Simão M., Prado F.O.C., Wahab O.A., Avila A.R. TempCharBERT: Keystroke Dynamics for Continuous Access Control Based on Pre-Trained Language Models. In: 2024 IEEE International Workshop on Information Forensics and Security (WIFS), 02–05 December 2024, Rome, Italy. IEEE; 2024. P. 1–6. https://doi.org/10.1109/WIFS61860.2024.10810697

12. Putra S.R., Chowanda A. Keystroke Dynamics on Multi-Session and Uncontrolled Settings Using CNN Bi-LSTM. Journal of Theoretical and Applied Information Technology. 2025;103(2):506–516. https://doi.org/10.5281/zenodo.15762286

13. Ermisheva Yu.D., Omelchenko T.A. Separate Results of the Application of the Software Authentication Tool by Keystroke Dynamics. NBI Technologies. 2023;17(1):11–16. (In Russ.). https://doi.org/10.15688/NBIT.jvolsu.2023.1.2

14. Kaurov A.V. Metod identifikatsii sub"ektov putem ispol'zovaniya algoritma klaviaturnogo podcherka. Symbol of Science. 2022;(7–2):6–7. (In Russ.).

15. Sharma A., Jureček M., Stamp M. Keystroke Dynamics for User Identification. arXiv. URL: https://arxiv.org/abs/2307.05529 [Accessed 12th August 2025].

16. Linnik E.A., Triphonov G.I., Fedorova E.V., Mitrophanova S.V. The Method of the Automated Workplace Protection and the System of Its Implementation. Vozdushno-kosmicheskie sily. Teoriya i praktika. 2022;(24):53–62. (In Russ.).

17. Senerath D., Tharinda S., Vishvajith M., Rasnayaka S., Wickramanayake S., Meedeniya D. BehaveFormer: A Framework with Spatio-Temporal Dual Attention Transformers for IMU-Enhanced Keystroke Dynamics. In: 2023 IEEE International Joint Conference on Biometrics (IJCB), 25–28 September 2023, Ljubljana, Slovenia. IEEE; 2023. P. 1–9. https://doi.org/10.1109/IJCB57857.2023.10448997

18. Wahab A., Hou D., Cheng N., Huntley P., Devlen Ch. Impact of Data Breadth and Depth on Performance of Siamese Neural Network Model: Experiments with Three Keystroke Dynamic Datasets. arXiv. URL: https://arxiv.org/abs/2501.07600 [Accessed 18th August 2025].

19. Shklyar E.V. An Algorithm for Generating Word Lists with a Specified Bigram Distribution for Keystroke Dynamics Biometric Template Registration. IT Security (Russia). 2025;32(3):74–89. (In Russ.).