The study of behavioral biometrics using data analysis and machine learning methods

The article shows the possibilities of using machine learning methods to build and analyze an authentication system based on the dynamics of keystrokes. The paper substantiates the need to improve the multifactor authentication system. A method of classifying the work of behavioral biometrics for comparison and use of research results is proposed. The basic possibilities of processing and generating dynamic and static signs of the dynamics of keystrokes are considered. Various combinations of feature sets and training samples were tested, and the best combination with an Equal Error Rate (EER) of 4.7% was described. An iterative analysis of the quality of the system allows us to establish the importance of the first characters of the input sequence, as well as the nonlinear relationship between the degree of ranking of the model and EER. The high performance achieved by the boosting model indicates the significant potential of behavioral authentication for further improvement, development and application. The significance of this method, its practical usefulness not only in the task of authentication, development prospects, including the use of neural network methods and data dynamics analysis are presented. Despite the achieved results, there is a need for further work on the model, including the development of additional clustering, classification models, changing the set of features and building a cascade. The importance of the research area, which can make a significant contribution to the development of information security and technology, is emphasized.

1. Obaidat M.S. A verification methodology for computer systems users. In: SAC '95: 1995 Symposium on Applied Computing, 26-28 February 1995, Nashville, USA. New York: Association for Computing Machinery; 1995. P. 258–262. https://doi.org/10.1145/315891.315976

2. Roshanbin N., Miller J. Enhancing CAPTCHA Security Using Interactivity, Dynamism, and Mouse Movement Patterns. International Journal of Systems and Service-Oriented Engineering. 2016;6(1):17–36. https://doi.org/10.4018/ijssoe.2016010102

3. Chang L., Shi F., Taghizadeh-Hesary F., Saydaliev H.B. Information and communication technologies development and the resource curse. Resources Policy. 2023;80. https://doi.org/10.1016/j.resourpol.2022.103123

4. Saini B.S., Kaur N., Bhatia K.S. Keystroke Dynamics for Mobile Phones: A Survey. Indian Journal of Science and Technology. 2016;9(6). https://doi.org/10.17485/ijst/2016/v9i6/82084

5. Dhakal V., Feit A.M., Kristensson P.O., Oulasvirta A. Observations on Typing from 136 Million Keystrokes. In: CHI '18: CHI Conference on Human Factors in Computing Systems, 21-26 April 2018, Montreal, QC, Canada. New York: Association for Computing Machinery; 2018. https://doi.org/10.1145/3173574.3174220

6. Lee H., Hwang J.Y., Kim D.I., Lee S., Lee S.-H., Shin J.S. Understanding Keystroke Dynamics for Smartphone Users Authentication and Keystroke Dynamics on Smartphones Built-In Motion Sensors. Security and Communication Networks. 2018;2018. https://doi.org/10.1155/2018/2567463

7. Georgiev M., Eberz S., Martinovic I. Techniques for Continuous Touch-Based Authentication. In: ISPEC 2022: The 17th International Conference on Information Security Practice and Experience, 23-25 November 2022, Taipei, Taiwan. Cham: Springer; 2022. P. 409–431. https://doi.org/10.1007/978-3-031-21280-2_23

8. Abernethy M., Rai S. Applying Feature Selection to Reduce Variability in Keystroke Dynamics Data for Authentication Systems. In: 13th Australian Information Warfare and Security Conference, 3-5 December 2012, Perth, Western Australia. Perth: SRI Security Research Institute, Edith Cowan University; 2012. P. 17–23. https://doi.org/10.4225/75/57a841bcbefaf

9. Messerman A., Mustafić T., Camtepe S.A., Albayrak S. Continuous and non-intrusive identity verification in real-time environments based on free-text keystroke dynamics. In: 2011 International Joint Conference on Biometrics (IJCB), 11-13 October 2011, Washington, DC, USA. IEEE; 2011. https://doi.org/10.1109/ijcb.2011.6117552

10. Stragapede G. et al. IEEE BigData 2023 Keystroke Verification Challenge (KVC). In: 2023 IEEE International Conference on Big Data (BigData), 15-18 December 2023, Sorrento, Italy. IEEE; 2024. P. 6092–6100. https://doi.org/10.1109/BigData59044.2023.10386557

11. Usman A.K., Shah M.H. Strengthening E-Banking security using Keystroke Dynamics. Journal of Internet Banking and Commerce. 2013;18(3). URL: https://www.icommercecentral.com/open-access/strengthening-ebanking-security-using-keystroke-dynamics.php?aid=38267

12. Shah A., Shah P., Shah H., Bhadane C. Strengthening user Authentication using Keystroke Dynamics. International Journal of Engineering Research & Technology. 2015;4(11).

13. Stragapede G., Delgado-Santos P., Tolosana R., Vera-Rodriguez R., Guest R., Morales A. TypeFormer: Transformers for Mobile Keystroke Biometrics. URL: https://doi.org/10.48550/arXiv.2212.13075 (Accessed 10th April 2024).

14. Özbek M.E. A flexible approach for biometric menagerie on user classification of keystroke data. Journal of Electrical Engineering. 2023;74(1). https://doi.org/10.2478/jee-2023-0003

15. Teh P.S., Teoh A.B.J., Yue S. A Survey of Keystroke Dynamics Biometrics. The Scientific World Journal. 2013;2013. https://doi.org/10.1155/2013/408280

16. Guzairov M.B., Ismagilova A.S., Lushnikov N.D. Authentication of information system users by facial image. Modelirovanie, optimizatsiya i informatsionnye tekhnologii = Modeling, Optimization and Information Technology. 2023;11(4). (In Russ.). https://doi.org/10.26102/2310-6018/2023.43.4.017