KEYSTROKE DYNAMICS RECOGNITION USING NINE-VARIATE PREDICTION ELLIPSOID FOR NORMALIZED DATA
DOI:
https://doi.org/10.15588/1607-3274-2025-1-9Keywords:
keystroke dynamics recognition, multivariate Box-Cox transformation, prediction ellipsoid, normalizing transformation.Abstract
Context. Keystroke dynamics recognition is a crucial element in enhancing security, enabling personalized user authentication, and supporting various identity verification systems. This study investigates the influence of data distribution on the performance of one-class classification models in keystroke dynamics, focusing on the application of a nine-variate prediction ellipsoid. The object of research is the keystroke dynamics recognition process. The subject of the research is a mathematical model for keystroke dynamics recognition. Unlike typical approaches assuming a multivariate normal distribution of data, real-world keystroke datasets often exhibit non-Gaussian distributions, complicating model accuracy and robustness. To address this, the dataset underwent normalization using the multivariate Box-Cox transformation, allowing the construction of a more precise decision boundary based on the prediction ellipsoid for normalized data.
The objective of the work is to increase the probability of keystroke dynamics recognition by constructing a nine-variate prediction ellipsoid for normalized data using the Box-Cox transformation.
Method. This research involves constructing a nine-variate prediction ellipsoid for data normalized using the Box-Cox transformation to improve keystroke dynamics recognition. The squared Mahalanobis distance is applied to identify and remove outliers, while the Mardia test assesses deviations from normality in the multivariate distribution. Estimates for parameters of multivariate Box-Cox transformation are derived using the maximum likelihood method.
Results. The results demonstrate significant performance improvements after normalization, reaching higher accuracy and robustness compared to models built for non-normalized data. The application of the nine-variate Box-Cox transformation successfully accounted for feature correlations, enabling the prediction ellipsoid to better capture underlying data patterns.
Conclusions. For keystroke dynamics recognition, a mathematical model in the form of the nine-variate prediction ellipsoid for data normalized using the multivariate Box-Cox transformation has been developed, which enhances the probability of recognition compared to models constructed for non-normalized data. However, challenges remain in determining the optimal normalization technique and selecting the significance level for constructing the prediction ellipsoid. These findings underscore the importance of careful feature selection and advanced data normalization techniques for further research in keystroke dynamics recognition.
References
Dias T., Vitorino J., Maia E., Sousa O., Praça I. KeyRecs: A keystroke dynamics and typing pattern recognition dataset, Data in Brief, 2023, Vol. 50, pp. 1–8. DOI: 10.1016/j.dib.2023.109509
Alshehri A., Coenen F., Bollegala D. Accurate continuous and non-intrusive user authentication with multivariate keystroke streaming, 9th International Conference on
Knowledge Discovery and Information Retrieval, Funchal, 1–3 November, 2017 : proceedings. Funchal, SciTePress, 2017, pp. 61–70. DOI: 10.5220/0006497200610070
Ismail M., Salem M., Abd El Ghany M.et al. Outlier detection for keystroke biometric user authentication, PeerJ Computer Science, 2024, Vol. 50. DOI: 10.7717/peerjcs.2086
Oyebola O. Examining the distribution of keystroke dynamics features on computer, tablet and mobile phone platforms, Mobile Computing and Sustainable Informatics: Proceedings of ICMCSI 2023, Nepal, 11–12 January, 2023 : proceedings. Singapore, Springer Nature Singapore 2023, pp. 613–620 DOI: 10.1007/978-981-99-0835-6_43
Saini B., Singh P., Nayyar A. , et al. A three-step authentication model for mobile phone user using keystroke dynamics, IEEE Access, 2020, Vol. 10, pp. 125909–125922. DOI: 10.1109/ACCESS.2020.3008019
Anusas-Amornkul N. Strengthening password authentication using keystroke dynamics and smartphone sensors, ICICM 2019: Proceedings of the 9th International Conference on Information Communication and Management, Prague, 23–26 August, 2019 : proceedings.
New York, Association for Computing Machinery, 2019, pp. 70–74. DOI: 10.1145/3357419.3357425
Fierrez J., Pozo A., Martinez-Diaz M. et al. Benchmarking touchscreen biometrics for mobile authentication, IEEE Transactions on Information Forensics and Security, 2018. Vol. 13, № 11, pp. 2720–2733. DOI: 10.1109/TIFS.2018.2833042
Li Q. Chen H. CDAS: A continuous dynamic authentication system, Proceedings of the 2019 8th International Conference on Software and Computer Applications, Penang, 19–21 February, 2019, proceedings. New York, Association for Computing Machinery, 2019, pp. 447–
DOI: 10.1145/3316615.3316691
Chen L., Zhong Y., Ai W. et al. Continuous authentication based on user interaction behavior / [L. Chen,] // 2019 7th International Symposium on Digital Forensicsand Security (ISDFS), Barcelos, 10–12 June, 2019 : proceedings. Barcelos, IEEE, 2019, pp. 1–6. DOI: 10.1109/ISDFS.2019.8757539
Baynath P., Soyjaudah K., Khan M. Keystroke recognition using neural network, 2017 5th International Symposium on Computational and Business Intelligence(ISCBI), Dubai, 11–14 August, 2017 : proceedings. Dubai, IEEE, 2017, pp. 86–90. DOI:10.1109/ISCBI.2017.8053550
Andrean A., Jayabalan M., Thiruchelvam V. Keystroke dynamics based user authentication using deep multilayer perceptron, International Journal of Machine Learning and Computing, 2020, Vol. 10, № 1, pp. 134–139. DOI: 10.18178/ijmlc.2020.10.1.910
Sharma A., Jureček M., Stamp M. Keystroke dynamics for user identification, arXiv preprint arXiv:2307.05529, 2023, pp. 1–22. DOI: 10.48550/arXiv.2307.05529
Raul N., Shankarmani R., Joshi P. A comprehensive review of keystroke dynamics-based authentication mechanism, International Conference on Innovative Computing and Communications. Advances in Intelligent Systems and Computing, Delhi, 20–21 February, 2021:proceedings. Singapore, Springer, 2021, Vol. 1059, pp.149–162 DOI: 10.1007/978-981-15 03245_13
Antal M., Szabó L. An evaluation of one-class and twoclass classification algorithms for keystroke dynamics authentication on mobile devices, 2015 20th International Conference on Control Systems and Computer Science, Bucharest, 27–29 May, 2015 : proceedings. Bucharest, IEEE, 2015, pp. 343–350. DOI: 10.1109/CSCS.2015.16
Marques H., Swersky L., Sander J. et al. On the evaluation of outlier detection and one-class classification: a comparative study of algorithms, model selection, and ensembles, Data Mining and Knowledge Discovery, 2023, Vol. 37, pp. 1–45. DOI: 10.1007/s10618-023-00931-x
Toosi R., Akhaee M. Time-frequency analysis of keystroke dynamics for user authentication, Future Generation Computer Systems, 2021, Vol. 115, pp. 438–447. DOI:10.1016/j.future.2020.09.027
Jawed H., Ziad Z., Khan M. et al. Anomaly detection through keystroke and tap dynamics implemented via machine learning algorithms, Turkish Journal of Electrical Engineering and Computer Sciences, 2018, Vol. 26, № 4, pp. 1698–1709. DOI: 10.3906/elk-1711-410
Ceker H., Upadhyaya S. User authentication with keystroke dynamics in long-text data, 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS), Niagara Falls, 6–9 September, 2016. Niagara Falls, IEEE, 2016, pp. 1–6. DOI:
1109/BTAS.2016.7791182
Patel Y., Ouazzane K., Vassilev V. et al. Keystroke dynamics using auto encoders, 2019 International Conference on Cyber Security and Protection of Digital Services, Oxford, 3–4 June, 2019 : proceedings. Oxford, IEEE, 2019, pp. 1–8.
DOI: 10.1109/CyberSecPODS.2019.8885203
Centeno M., Moorsel A., Castruccio S. Smartphone continuous authentication using deep learning autoencoders, 15th Annual Conference on Privacy, Security and Trust (PST), Calgary, 28–30 August, 2017 : proceedings. Calgary, IEEE, 2017, pp. 1470–1478.
DOI: 10.1109/PST.2017.00026
Eizaguirre-Peral I., Segurola-Gil L., Zola F. Conditional generative adversarial network for keystroke presentation attack, arXiv preprint arXiv:2212.08445, 2022, pp. 1–4.
DOI: 10.48550/arXiv.2212.08445
Kim S., Park D., Jung J. Evaluation of one-class classifiers for fault detection: Mahalanobis classifiers and the Mahalanobis-Taguchi system, Processes, 2021, Vol. 9, № 8, P. 1450.
DOI: 10.3390/pr9081450
Bezerra V., Da Costa V., Barbon Junior S.et al. IoTDS: A one-class classification approach to detect botnets in Internet of Things devices, Sensors, 2019, Vol. 19, № 14, P. 3188.
DOI: 10.3390/s19143188
Prykhodko S. B., Shutko I. S., Prykhodko A. S. A nonlinear regression model to estimate the size of web apps created using the CakePHP framework, Radio Electronics, Computer Science, Control, 2021, Vol. 59, № 4, pp. 129–139. DOI: 10.15588/1607-3274-2021-4-12
Lam K., Meijer K., Loonstra F. et al. Real-world keystroke dynamics are a potentially valid biomarker for clinical disability in multiple sclerosis, Multiple Sclerosis Journal, 2021, Vol. 27, № 4, pp. 1421–1431. DOI: 10.1177/1352458520968797
Prykhodko S., Trukhov A. Face recognition using the ten-variate prediction ellipsoid for normalized data based on the Box-Cox transformation, Radio Electronics, Computer Science, Control, 2024, Vol. 2, pp. 82–89. DOI: 10.15588/1607-3274-2024-2-9
Prykhodko S., Trukhov A. Application of a ten-variate prediction ellipsoid for normalized data and machine learning algorithms for face recognition, CMIS-2024: Seventh International Workshop on Computer Modeling and Intelligent Systems, Zaporizhzhia, 3 May, 2024 : proceedings. Aachen, CEUR, 2024, pp. 362–375.
Nurmaini S., Darmawahyuni A., Sakti Mukti A.et al. Deep learning-based stacked denoising and autoencoder for ECG heartbeat classification, Electronics, 2020, Vol. 9, № 1, P. 135. DOI: 10.3390/electronics9010135
Prykhodko S., Prykhodko N., Makarova L. et al. Detecting outliers in multivariate non-Gaussian data on the basis of normalizing transformations, 2017 IEEE First Ukraine Conference on Electrical and Computer Engineering, Kyiv, 29 May – 2 June, 2017 : proceedings.
New York, IEEE, 2017, pp. 846–849. DOI: 10.1109/UKRCON.2017.8100366
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 S. B. Prykhodko , A. S. Trukhov
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Creative Commons Licensing Notifications in the Copyright Notices
The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.
The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.
The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.
Authors who publish with this journal agree to the following terms:
-
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
-
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
-
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
