Building A Keystroke Dynamic Recognition System Using An Improved Accelerated Method

Abstract

A trustworthy security application in the actual world uses the keystroke capability of typing recognition software. Despite being straightforward, it requires a quick and precise method of character analysis. In this manuscript, a keystroke dynamic recognition method to identify and block illegal users is proposed by using deep learning of convolutional neural networks (CNNs) which it can efficiently distinguish legitimate users from illegitimate users. Where, two proposed networks are built based on 1D-CNN to increase and accelerate the recognition abilities. The first network improves the system performance by modifying the kind of activation function utilized, whereas the second network improves the system performance by employing the residual scheme. The findings display that the suggested CNN model with the swish function can deny all illegitimate users with an average equal error rate (EER) of 0.0066. Furthermore, by parallel computing (GPU), the model performance is accelerated by approximately 2 times. Based on the outcomes, the suggested CNN model with swish function significantly outperforms other models in the literature.

Keywords

• Deep Learning
• Keystroke Dynamic
• Residual CNN
• Parallel Computing
• Authentication System

References

1. Altwaijry, N. (2020). Keystroke Dynamics Analysis for User Authentication Using a Deep Learning Approach. International Journal of Computer Science and Network Security, 20(12), 209–216. https://doi.org/10.22937/IJCSNS.2020.20.12.23
2. Andrean, A., Jayabalan, M., & Thiruchelvam, V. (2020). Keystroke Dynamics Based User Authentication using Deep Multilayer Perceptron. International Journal of Machine Learning and Computing, 10(1), 134–139. https://doi.org/10.18178/ijmlc.2020.10.1.910
3. Ceker, H., & Upadhyaya, S. (2017). Sensitivity analysis in keystroke dynamics using convolutional neural networks. 2017 IEEE Workshop on Information Forensics and Security, WIFS 2017, 2018-Janua, 1–6. https://doi.org/10.1109/WIFS.2017.8267667 Killourhy, K. (2009). "Keystroke dynamics – benchmark dataset", Carnegie-MellonUniversity, http://www.cs.cmu.edu/~keystroke/#sec2 ,
4. Killourhy, K. S., & Maxion, R. A. (2009). Comparing anomaly-detection algorithms for keystroke dynamics. 2009 IEEE/IFIP International Conference on Dependable Systems & Networks, 125–134. https://doi.org/10.1109/DSN.2009.5270346
5. Kim, J., & Kang, P. (2020). Freely typed keystroke dynamics-based user authentication for mobile devices based on heterogeneous features. Pattern Recognition, 108. https://doi.org/10.1016/j.patcog.2020.107556
6. Lemley, J., Bazrafkan, S., & Corcoran, P. (2017). Deep Learning for Consumer Devices and Services: Pushing the limits for machine learning, artificial intelligence, and computer vision. IEEE Consumer Electronics Magazine, 6(2), 48–56. https://doi.org/10.1109/MCE.2016.2640698
7. Lin, C. H., Liu, J. C., & Lee, K. Y. (2018). On neural networks for biometric authentication based on keystroke dynamics. Sensors and Materials, 30(3), 385–396. https://doi.org/10.18494/SAM.2018.1757
8. Maheshwary, S., Ganguly, S., & Pudi, V. (2017). Deep secure: A fast and simple neural network based approach for user authentication and identification via keystroke dynamics. IWAISe: First International Workshop on Artificial Intelligence in Security, August 2017, 59. https://api.semanticscholar.org/CorpusID:53459138

9. Mao, R., Wang, X., & Ji, H. (2022). ACBM: attention-based CNN and Bi-LSTM model for continuous identity authentication. Journal of Physics: Conference Series, 2352(1). https://doi.org/10.1088/1742-6596/2352/1/012005
10. Muniasamy, A. (2019). Applications of keystroke dynamics biometrics in online learning environments: A selective study. Biometric Authentication in Online Learning Environments, 97–121. https://doi.org/10.4018/978-1-5225-7724-9.ch005
11. Sahu, C., & Banavar, M. (2021). A nonlinear feature transformation-based multi-user classification algorithm for keystroke dynamics. Conference Record - Asilomar Conference on Signals, Systems and Computers, 2021-Octob(March 2022), 1448–1452. https://doi.org/10.1109/IEEECONF53345.2021.9723223
12. Wesołowski, T. E., Porwik, P., & Doroz, R. (2016). Electronic Health Record Security Based on Ensemble Classification of Keystroke Dynamics. Applied Artificial Intelligence, 30(6), 521–540. https://doi.org/10.1080/08839514.2016.1193715