Student authentication using typing dynamics and deep neural networks in online judge systems

• Ronem Matos Lavareda Filho Federal University of Amazonas http://orcid.org/0000-0002-4464-9587
• Juan Gabriel Colonna Federal University of Amazonas
• David B. F. de Oliveira Federal University of Amazonas http://orcid.org/0000-0002-2887-2324
• Edwin Juan L. B. Monteiro Federal University of Amazonas http://orcid.org/0000-0002-9623-3233
• Paulo Henrique Nellessen Gonçalves Federal University of Amazonas

DOI: https://doi.org/10.5753/sbie.2022.225779

Abstract

In online code verification systems student authentication is normally done only at the beginning of the login session. In these kind of systems sharing login and password information causes authenticity issues or identity spoofing. In this research, we present a method for authentication verification using the dynamics of typing. This technique does not require any explicit user action or additional hardware, only a keyboard. We use a Deep Neural Network architecture that was designed to automatically learn to recognize students’ typing patterns in exercises and assessments that took place in these systems. To validate the method, data from the typing dynamics of 42 students in the CodeBench online code system were used. Then, several experiments were performed that demonstrated the effectiveness of the proposed method.

Keywords: authentication, students, code verification systems, Deep Neural Network

References

Acien, A., Monaco, J. V., Morales, A., Vera-Rodriguez, R., e Fierrez, J. (2020). Typenet: Scaling up keystroke biometrics. arXiv preprint arXiv:2004.03627.

Byun, J., Park, J., e Oh, A. (2020). Detecting contract cheaters in online programming classes with keystroke dynamics. In Proceedings of the Seventh ACM Conference on Learning@ Scale, pages 273–276.

Chaves, J. O. M. (2014). Uma ferramenta de apoio ao processo de ensino-aprendizagem em disciplinas de programação de computadores por meio da integração dos juízes online ao moodle.

Chong, P., Elovici, Y., e Binder, A. (2019). User authentication based on mouse dynamics using deep neural networks: A comprehensive study. IEEE Transactions on Information Forensics and Security.

Feher, C., Elovici, Y., Moskovitch, R., Rokach, L., e Schclar, A. (2012). User identity verification via mouse dynamics. Information Sciences, 201:19–36.

Giot, R. e Rocha, A. (2019). Siamese networks for static keystroke dynamics authentication. In IEEE International Workshop on Information Forensics and Security.

Hao, Q., Smith IV, D. H., Iriumi, N., Tsikerdekis, M., e Ko, A. J. (2019). A systematic investigation of replications in computing education research. ACM Transactions on Computing Education (TOCE), 19(4):42.

Killourhy, K. S. e Maxion, R. A. (2009). Comparing anomaly-detection algorithms for keystroke dynamics. In 2009 IEEE/IFIP International Conference on Dependable Systems & Networks, pages 125–134. IEEE.

Lavareda Filho, R. M., Colonna, J. G., e Oliveira, D. B. F. (2020). Autenticação contínua de alunos utilizando biometria comportamental em ambiente juiz on-line. In Anais do XXXI Simpósio Brasileiro de Informática na Educação, pages 1193–1202. SBC.

Longi, K., Leinonen, J., Nygren, H., Salmi, J., Klami, A., e Vihavainen, A. (2015). Identification of programmers from typing patterns. In Proceedings of the 15th Koli Calling Conference on Computing Education Research, pages 60–67. ACM.

Peltola, P., Kangas, V., Pirttinen, N., Nygren, H., e Leinonen, J. (2017). Identification based on typing patterns between programming and free text. In Proceedings of the 17th Koli Calling International Conference on Computing Education Research, pages 163–167.

Silva, R. J. H., Pazoti, M. A., da Silva, F. A., Pereira, D. R., e de Almeida, L. L. (2019). Autenticação biométrica para sistemas por meio da dinâmica da digitação. In Colloquium Exactarum. ISSN: 2178-8332, volume 11, pages 26–33.

Ullah, A., Xiao, H., e Barker, T. (2019). A dynamic profile questions approach to mitigate impersonation in online examinations. Journal of Grid Computing, 17(2):209–223.

Xiaofeng, L., Shengfei, Z., e Shengwei, Y. (2019). Continuous authentication by free-text keystroke based on cnn plus rnn. Procedia computer science, 147:314–318.