Keystroke dynamics analysis using machine learning methods

• Autorzy: Shabliy Nataliya , Lupenko Serhii , Lutsyk Nadiia , Yasniy Oleh , Malyshevska Olha

Identyfikatory

DOI

10.23743/acs-2021-30

• Języki publikacji: EN

Abstrakty

EN

The primary objective of the paper was to determine the user based on its keystroke dynamics using the methods of machine learning. Such kind of a problem can be formulated as a classification task. To solve this task, four methods of supervised machine learning were employed, namely, logistic regression, support vector machines, random forest, and neural network. Each of three users typed the same word that had 7 symbols 600 times. The row of the dataset consists of 7 values that are the time period during which the particular key was pressed. The ground truth values are the user id. Before the application of machine learning classification methods, the features were transformed to z-score. The classification metrics were obtained for each applied method. The following parameters were determined: precision, recall, f1-score, support, prediction, and area under the receiver operating characteristic curve (AUC). The obtained AUC score was quite high. The lowest AUC score equal to 0.928 was achieved in the case of linear regression classifier. The highest AUC score was in the case of neural network classifier. The method of support vector machines and random forest showed slightly lower results as compared with neural network method. The same pattern is true for precision, recall and F1-score. Nevertheless, the obtained classification metrics are quite high in every case. Therefore, the methods of machine learning can be efficiently used to classify the user based on keystroke patterns. The most recommended method to solve such kind of a problem is neural network.

Słowa kluczowe

EN

keystroke dynamics analysis; machine learning; Neural Network; Supervised Learning; classification problem

PL

analiza dynamiki uderzeń klawiszy; uczenie maszynowe; sieć neuronowa; uczenie nadzorowane; problem klasyfikacji

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2021
• Tom: Vol. 17, no 4
• Strony: 75--83
• Opis fizyczny: Bibliogr. 26 poz., fig., tab.

Twórcy

autor

Shabliy Nataliya

• Ternopil Ivan Puluj National Technical University, Faculty of Computer Information Systems and Software Engineering, Computer Systems and Networks Department, Ternopil, Ukraine

• https://orcid.org/0000-0002-1125-4757

autor

Lupenko Serhii

• Ivan Puluj National Technical University, Faculty of Computer Information Systems and Software Engineering, Computer Systems and Networks Department, Ternopil, Ukraine

• https://orcid.org/0000-0002-6559-0721

autor

Lutsyk Nadiia

• Ivan Puluj National Technical University, Faculty of Computer Information Systems and Software Engineering, Computer Systems and Networks Department, Ternopil, Ukraine

• https://orcid.org/0000-0002-0361-6471

autor

Yasniy Oleh

• Ivan Puluj National Technical University, Faculty of Computer Information Systems and Software Engineering, Computer Systems and Networks Department, Ternopil, Ukraine

• https://orcid.org/0000-0002-9820-9093

autor

Malyshevska Olha

• Ivano-Frankivsk National Medical University, Department of Hygiene and Ecology, Ivano-Frankivsk, Ukraine

• https://orcid.org/0000-0003-0180-2112

Bibliografia

• [1] Al-Awad, N. A., Abboud, I. K., & Al-Rawi, M. F. (2021). Genetic Algorithm-PID controller for model order reduction pantographcatenary system. Applied Computer Science, 17(2), 28-39. https://doi.org/10.23743/acs-2021-11
• [2] Alyamani, A., & Yasniy, O. (2020). Classification of EEG signal by methods of machine learning. Applied Computer Science, 16(4), 56-63. https://doi.org/10.23743/acs-2020-29
• [3] Biau, G., & Scornet, E. (2016). A Random Forest Guided Tour. Test, 25(2), 197–227. https://doi.org/10.1007/s11749-016-0481-7
• [4] Bradley, A. P. (1997). The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognition, 30(7), 1145–1159. https://doi.org/10.1016/S0031-3203(96)00142-2
• [5] Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1–58. https://doi.org/10.1145/1541880.1541882
• [6] Dewi, W., & Utomo, W. H. (2021). Plant classification based on leaf edges and leaf morphological veins using wavelet convolutional neural network. Applied Computer Science, 17(1), 81–89. https://doi.org/10.23743/acs-2021-08
• [7] Dhir, Vijay, Singh, A., Kumar, R., & Singh, G. (2010). Biometric Recognition: A Modern Era For Security. International Journal of Engineering Science and Technology, 2(8), 3364–80.
• [8] Edgar, T. W., & Manz, D. O. (2017). Research Methods for Cyber Security. Syngress.
• [9] Fischer, R. J., Halibozek, E. P., & Walters, D. C. (2019). Holistic Security Through the Application of Integrated Technology. Introduction to Security, 2019, 433–62. https://doi.org/10.1016/b978-0-12-805310-2.00017-2.
• [10] Gaines, R. S., Lisowski. W., Press, S. J., & Shapiro, N. (1980). Authentication by Keystroke Timing. The Rand Corporation.
• [11] Gebrie, M. T., & Abie, H. (2017). Risk-Based Adaptive Authentication for Internet of Things in Smart Home EHealth. Proceedings of the 11th European Conference on Software Architecture: Companion Proceedings (ECSA'17) (pp. 102–108). Association for Computing Machinery. https://doi.org/10.1145/3129790.3129801
• [12] Hwang, S.-S., Lee H., & Cho, S. (2009). Improving Authentication Accuracy Using Artificial Rhythms and Cues for Keystroke Dynamics-Based Authentication. Expert Systems with Applications, 36(7), 10649–56. https://doi.org/10.1016/j.eswa.2009.02.075
• [13] Jain, A. K., Bolle, R. M., & Pankanti, S. (2006). Biometrics. Personal Identification in Networked Society. Springer.
• [14] Jain, A. K., Ross, A., & Prabhakar, S. (2004). An Introduction to Biometric Recognition. IEEE Trans. on Circuits and Systems for Video Technology, 14(1), 4-19.
• [15] Javaheri, S. H., Sepehri, M. M. & Teimourpour, B. (2013). Response Modeling in Direct Marketing. A Data Mining-Based Approach for Target Selection. Data Mining Applications with R (pp. 153-180). Elsevier Inc. https://doi.org/10.1016/B978-0-12-411511-8.00006-2
• [16] Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43(1), 59–69.
• [17] Markou, M., & Singh, S. (2003). Novelty detection: a review—part 1: statistical approaches. Signal Processing, 83(12), 2481–2497. https://doi.org/10.1016/j.sigpro.2003.07.018
• [18] Miljković, D. (2010). Review of novelty detection methods. The 33rd International Convention MIPRO (pp. 593-598). IEEE.
• [19] Monrose, F., Reiter, M. K., & Wetzel, S. (2002). Password Hardening Based on Keystroke Dynamics. International Journal of Information Security, 1(2), 69–83. https://doi.org/10.1007/s102070100006
• [20] Raschka, S. (2017). Python Machine Learning. Second edition. Packt Publishing Ltd.
• [21] Ru, W.G., & Eloff, J.H. (1997). Enhanced Password Authentication through Fuzzy Logic. IEEE Expert, 12, 38-45.
• [22] Sridharan, M., Rani Arulanandam, D. C., Chinnasamy, R. K., Thimmanna, S., & Dhandapani, S. (2021). Recognition of font and tamil letter in images using deep learning. Applied Computer Science, 17(2), 90–99. https://doi.org/10.23743/acs-2021-15
• [23] Subasi, A. (2020). Practical Machine Learning for Data Analysis Using Python. Academic Press.
• [24] Umphress, D., & Williams, G. (1985). Identity verification through keyboard characteristics. International Journal of Man-Machine Studies, 23(3), 263–273. https://doi.org/10.1016/S0020-7373(85)80036-5
• [25] Vaibhaw, Sarraf, J., & Pattnaik, P.K. (2020). Brain–Computer Interfaces and Their Applications. An Industrial IoT Approach for Pharmaceutical Industry Growth, 2, 31-54. https://doi.org/10.1016/b978-0-12-821326-1.00002-4
• [26] Williams, B., Halloin, C., Löbel, W., Finklea, F., Lipke, E., Zweigerdt, R., & Cremaschi, S. (2020). Data-Driven Model Development for Cardiomyocyte Production Experimental Failure Prediction. Computer Aided Chemical Engineering, 48, 1639-1644. https://doi.org/10.1016/B978-0-12-823377-1.50274-3

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).