Authentication Using Keystrokes Dynamic For Static Text With Hybrid Deep Learning Technique
DOI:
https://doi.org/10.29284/3zz3bb45Keywords:
Keystroke Dynamics, Deep Learning, BiLSTM, Capsule Network, Feature Fusion.Abstract
The Behavioral authentication via keystroke dynamics provides a non-intrusive and hardware-independent means of identity verification. However, prior deep-learning approaches often suffer from class imbalance and limited generalization. This study proposes a hybrid deep-learning model combining multi-head feature fusion, Conv1D layers, capsule networks, bidirectional LSTM, attention mechanisms, and Monte Carlo dropout for static-text authentication. To mitigate imbalance in the CMU Keystroke Dynamics dataset, oversampling and class-weighted loss were employed. The model was trained for 20 epochs and evaluated through five-fold cross-validation. Experimental results yield an accuracy of 99.3%, outperforming recent baselines. The proposed framework effectively captures spatial temporal dependencies and quantifies uncertainty, contributing a robust and interpretable solution for real-time behavioral authentication.
References
1. Gandomi, A. and Haider, M., 2015. Beyond the hype: Big data concepts, methods, and analytics. International Journal of Information Management, 35(2), pp.137–144.
2. Zhou, B., Chen, Z., Zhang, Y., Zeng, D. and Zhang, Y., 2016. Smart city development and the identification of core domains. Cities, 42, pp.1–10.
3. Zhao, L., Tang, Z.Y. and Zou, X., 2019. Mapping the knowledge domain of smart-city research: A bibliometric and scientometric analysis. Sustainability, 11(23), p.6648.
4. Wu, Z., Jiang, M., Li, H. and Zhang, X., 2022. Mapping the knowledge domain of smart city development to urban sustainability: a scientometric study. In Sustainable Smart City Transitions (pp. 28-52). Routledge.
5. Wang, A., Zhang, A., Chan, E.H., Shi, W., Zhou, X. and Liu, Z., 2020. A review of human mobility research based on big data and its implication for smart city development. ISPRS International Journal of Geo-Information, 10(1), p.13.
6. Hsu, W.L., Qiao, M., Xu, H., Zhang, C., Liu, H.L. and Shiau, Y.C., 2021. Smart city governance evaluation in the era of internet of things: An empirical analysis of Jiangsu, China. Sustainability, 13(24), p.13606.
7. Jordan, M.I. and Mitchell, T.M., 2015. Machine learning: Trends, perspectives, and prospects. Science, 349(6245), pp.255–260.
8. LeCun, Y., Bengio, Y. and Hinton, G., 2015. Deep learning. Nature, 521(7553), pp.436–444.
9. Ding, N., Qin, Y., Yang, G., Wei, F., Yang, Z., Su, Y., Hu, S., Chen, Y., Chan, C.M., Chen, W. and Yi, J., 2023. Parameter-efficient fine-tuning of large-scale pre-trained language models. Nature machine intelligence, 5(3), pp.220-235.
10. Madani, A., Krause, B., Greene, E.R., Subramanian, S., Mohr, B.P., Holton, J.M., Olmos Jr, J.L., Xiong, C., Sun, Z.Z., Socher, R. and Fraser, J.S., 2023. Large language models generate functional protein sequences across diverse families. Nature biotechnology, 41(8), pp.1099-1106.
11. Zhang, Z., Zhao, Y., Chen, Y., Lyu, X. and Wu, Y., 2017. Deep learning in omics: A survey and guideline. Briefings in Functional Genomics, 17(5), pp.351–363.
12. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
13. S. Sabour, N. Frosst, and G. E. Hinton, “Dynamic Routing Between Capsules,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
14. Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012. ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, pp.1097–1105.
15. Doshi-Velez, F. and Kim, B., 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608.
16. Kotsiantis, S.B., Zaharakis, I. and Pintelas, P., 2007. Supervised machine learning: A review of classification techniques. Emerging artificial intelligence applications in computer engineering, 160(1), pp.3–24.
17. Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H. and Neubig, G., 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. ACM computing surveys, 55(9), pp.1-35.
18. Abioye, S.O., Oyedele, L.O., Akanbi, L., Ajayi, A., Delgado, J.M.D., Bilal, M., Akinade, O.O. and Ahmed, A., 2021. Artificial intelligence in the construction industry: A review of present status, opportunities and future challenges. Journal of Building Engineering, 44, p.103299.
19. An, Q., Rahman, S., Zhou, J. and Kang, J.J., 2023. A comprehensive review on machine learning in healthcare industry: classification, restrictions, opportunities and challenges. Sensors, 23(9), p.4178.
20. Wang, X., & Hou, D. (2024). Enhancing Keystroke Dynamics Authentication with Ensemble Learning and Data Resampling Techniques. Electronics, 13(22), 4559.
21. Wyciślik, Ł., Wylężek, P., & Momot, A. (2024). The Improved Biometric Identification of Keystroke Dynamics Based on Deep Learning Approaches. Sensors, 24(12), 3763.
22. Risto, H. N., & Graven, O. H. (2024). Fixed-text keystroke dynamics authentication data set—collection and analysis. Annals of Telecommunications, 79(11), 731-743.
23. RENUKA, S., & KUMAR, N. S. (2024). HYBRID AUTHENTICATION: CNN-BILSTM KEYSTROKE DYNAMICS AND HOUGH-BASED FINGERPRINT VERIFICATION. Journal of Theoretical and Applied Information Technology, 102(19).
24. Teotia, T., Sharma, M., & Elmiligi, H. (2023). A comprehensive study of machine learning approaches for keystroke dynamics authentication. International Journal of Biometrics, 15(5), 560-586.
25. Stragapede, G., Delgado-Santos, P., Tolosana, R., Vera-Rodriguez, R., Guest, R., & Morales, A. (2024). TypeFormer: Transformers for mobile keystroke biometrics. Neural Computing and Applications, 36(29), 18531-18545.
26. Arsh, A., Kar, N., Das, S., & Deb, S. (2024). Multiple approaches towards authentication using keystroke dynamics. Procedia Computer Science, 235, 2609-2618.
27. AbdelRaouf, H., Chelloug, S. A., Muthanna, A., Semary, N., Amin, K., & Ibrahim, M. (2023). Efficient convolutional neural network-based keystroke dynamics for boosting user authentication. Sensors, 23(10), 4898.
28. Stylios, I., Chatzis, S., Thanou, O., & Kokolakis, S. (2023). Continuous authentication with feature-level fusion of touch gestures and keystroke dynamics to solve security and usability issues. Computers & Security, 132, 103363.
29. Stragapede, G., Delgado-Santos, P., Tolosana, R., Vera-Rodriguez, R., Guest, R., & Morales, A. (2023, January). Mobile keystroke biometrics using transformers. In 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) (pp. 1-6). IEEE.
30. Senarath, D., Tharinda, S., Vishvajith, M., Rasnayaka, S., Wickramanayake, S., & Meedeniya, D. (2023, September). Behaveformer: A framework with spatio-temporal dual attention transformers for imu-enhanced keystroke dynamics. In 2023 IEEE International Joint Conference on Biometrics (IJCB) (pp. 1-9). IEEE.
31. Li, T., Sahu, A.K., Talwalkar, A. and Smith, V., 2020. Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine, 37(3), pp.50-60
32. Kaissis, G.A., Makowski, M.R., Rückert, D. and Braren, R.F., 2020. Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence, 2(6), pp.305-311.
33. Yang, Q., Liu, Y., Chen, T. and Tong, Y., 2019. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2), pp.1-19.
34. Chang, H.C., Li, J., Wu, C.S. and Stamp, M., 2022. Machine learning and deep learning for fixed-text keystroke dynamics. In Artificial intelligence for cybersecurity (pp. 309-329). Cham: Springer International Publishing.
35. Carnegie Mellon University. CMU Keystroke Dynamics Benchmark Data Set. Available at: https://www.cs.cmu.edu/~keystroke/. Accessed May 2025.
36. Khatun, M. A., Yousuf, M. A., Turna, T. N., Azad, A. K. M., Alyami, S. A., & Moni, M. A. (2025). A Multi-Agent and Attention-Aware Enhanced CNN-BiLSTM Model for Human Activity Recognition for Enhanced Disability Assistance. Diagnostics, 15(5), 537.
37. Wyciślik, Ł., Wylężek, P., & Momot, A. (2024). The Improved Biometric Identification of Keystroke Dynamics Based on Deep Learning Approaches. Sensors, 24(12), 3763.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
