Journal of Cyber Security and Risk Auditing

Journal of Cyber Security and Risk Auditing

ISSN: 3079-5354 (Online)

Publishing model:

: Open access
Scopus Indexed
2025
14.7

CiteScore

Q1
open accessOpen Access

Article

👁️158views

Student Identity Fraud Detection in Online Exams Using Keystroke Dynamics: A Comparative Study of Classical Machine Learning and Deep Learning Models

by 

Khadija Alhumaid Orcid link

PDF logoPDF

Published: 2026/03/31

Abstract

The process of conducting online examinations has created a new security threat which allows students to use their authentic identity verification systems to impersonate others for assessment completion. The paper presents an identity verification system which uses keystroke dynamics as its core mechanism. The approach creates a biometric typing signature by analyzing password typing through latency and hold-time features. A benchmark study is conducted using the CMU Keystroke Dynamics dataset (DSL-StrongPasswordData). The researchers trained multiple classical Machine Learning (ML) models and Deep Learning (DL) architectures to identify multiple student groups while measuring their performance with Accuracy, Precision, Recall, F1-score, and ROC curves. The classical ML methods achieved better results than DL methods when tested on the tabular behavioral biometric dataset. The Random Forest model achieves the best performance with Accuracy = 94.07%, Precision = 94.22%, Recall = 94.07%, and F1 = 94.03%. The results demonstrate that recurrent architectures outperformed convolutional architectures because BiGRU achieved an accuracy of 88.14%. Advanced visualization techniques enable users to see how identity similarity patterns and behavioral drift and fraud risk separation exist in the data. The findings support the deployment of keystroke-based authentication as a low-cost additional security layer for academic integrity in remote proctored examinations.

Keywords

Academic IntegrityBiometricsDeep LearningKeystroke DynamicsMachine LearningOnline Exams Student Identity Fraud.

Doi Link

https://doi.org/10.63180/jcsra.thestap.2026.1.6

How to Cite the Article

Alhumaid, K. (2026). Student Identity Fraud Detection in Online Exams Using Keystroke Dynamics: A Comparative Study of Classical Machine Learning and Deep Learning Models. Journal of Cyber Security and Risk Auditing, 2026(1), 113–132. https://doi.org/10.63180/jcsra.thestap.2026.1.6

Student Identity Fraud Detection in Online Exams Using Keystroke Dynamics: A Comparative Study of Classical Machine Learning and Deep Learning Models is licensed under CC BY 4.0CCBY

References

  1. Al-Tamimi, S., & Al-Haija, Q. A. (2025). Security and privacy of educational computational intelligence. In Internet of Behavior-Based Computational Intelligence for Smart Education Systems (pp. 301–328). IGI Global Scientific Publishing.
  2. Salloum, S. A., Mhamdi, C., Al Kurdi, B., & Shaalan, K. (2018). Factors affecting the adoption and meaningful use of social media: A structural equation modeling approach. International Journal of Information Technology and Language Studies, 2(3), 96–109.
  3. Heil, J., & Ifenthaler, D. (2023). Online assessment in higher education: A systematic review. Online Learning, 27(1), 187–218.
  4. Salloum, S., Gaber, T., Vadera, S., & Shaalan, K. (2021). Phishing email detection using natural language processing techniques: A literature survey. Procedia Computer Science, 189, 19–28.
  5. Salloum, S., Gaber, T., Vadera, S., & Shaalan, K. (2022). A systematic literature review on phishing email detection using natural language processing techniques. Ieee Access, 10, 65703-65727.
  6. Dawson, P. (2020). Defending assessment security in a digital world: Preventing e-cheating and supporting academic integrity in higher education. Routledge.
  7. Al-Maroof, R. S., Alnazzawi, N., Akour, I., Ayoubi, K., Alhumaid, K., Nasser, N. M., ... & Salloum, S. (2022). Students' perception towards using electronic feedback after the pandemic: Post-acceptance study. International Journal of Data & Network Science, 6(4).
  8. Akçapınar, G. (2025). Detecting AI-assisted cheating in online exams through behavior analytics. arXiv. https://doi.org/10.48550/arXiv.2510.18881
  9. Killourhy, K. S., & Maxion, R. A. (2009, June). Comparing anomaly-detection algorithms for keystroke dynamics. In 2009 IEEE/IFIP international conference on dependable systems & networks (pp. 125-134). IEEE.
  10. Al-Tamimi, S., Al-Haija, Q. A., & AlShuaibi, A. (2025). Gamification in cybersecurity education: Insights, challenges, and emerging solutions. In Proceedings of the 2025 IEEE 16th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON) (pp. 526–532). IEEE.
  11. Abba, S. S., Obioha-Val, O. A., Ejiofor, V. O., Olaniyi, O. M., & Mayeke, N. R. (2025). Behavioral biometrics-powered continuous authentication for zero-trust remote work environments: A multi-factor identity verification framework. Asian Journal of Research in Computer Science, 18(12), 20–41.
  12. Salturk, S., Pamukcu, T. E., & Kahraman, N. (2026). Contactless biometric verification from in-air signatures using deep siamese networks. Scientific Reports, 16(1), 130.
  13. Shadman, R., Wahab, A. A., Manno, M., Lukaszewski, M., Hou, D., & Hussain, F. (2025). Keystroke dynamics: Concepts, techniques, and applications. ACM Computing Surveys, 57(11), 1–35.
  14. Agrawal, A. (2026). Human Behavior-Based Keystroke Password Authentication: A Behavioral Biometrics Approach. Exploring the Intersection of Forensics and Biometrics, 61-82.
  15. Giot, R., El-Abed, M., & Rosenberger, C. (2009, May). Keystroke dynamics authentication for collaborative systems. In 2009 International Symposium on Collaborative Technologies and Systems (pp. 172-179). IEEE.
  16. Teh, P. S., Teoh, A. B. J., & Yue, S. (2013). A survey of keystroke dynamics biometrics. The Scientific World Journal, 2013, Article 408280.
  17. Sing, T., Sander, O., Beerenwinkel, N., & Lengauer, T. (2005). ROCR: Visualizing classifier performance in R. Bioinformatics, 21(20), 3940–3941.
  18. Valdez, M. G., Merelo, J. J., Aguila, A. H., & Soto, A. M. (2017, November). Mining of keystroke and mouse dynamics to increase the engagement of students with programming assignments. In International Joint Conference on Computational Intelligence (pp. 41-61). Cham: Springer International Publishing.
  19. Sadikan, S. F. N., Ramli, A. A., & Fudzee, M. F. M. (2019). A survey paper on keystroke dynamics authentication for current applications. In AIP Conference Proceedings, 2173(1), Article 20010.
  20. Al Tamimi, S. (2025). Towards beyond technology: Reviewing human error (HE) as the primary reason of cybersecurity breaches. In Proceedings of the 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) (pp. 1–6).
  21. Lu, X., Zhang, S., Hui, P., & Lio, P. (2020). Continuous authentication by free-text keystroke based on CNN and RNN. Computers & Security, 96, Article 101861.
  22. Kochegurova, E. A., & Zateev, R. P. (2022). Hidden monitoring based on keystroke dynamics in online examination system. Programming and Computer Software, 48(6), 385–398.
  23. Shi, Y., Wang, X., Zheng, K., & Cao, S. (2023). User authentication method based on keystroke dynamics and mouse dynamics using HDA. Multimedia Systems, 29(2), 653–668.
  24. Wang, X., Shi, Y., Zheng, K., Zhang, Y., Hong, W., & Cao, S. (2022). User authentication method based on keystroke dynamics and mouse dynamics with scene-irrelevant features in hybrid scenes. Sensors, 22(17), Article 6627.
  25. Zhong, Y., Deng, Y., & Jain, A. K. (2012, June). Keystroke dynamics for user authentication. In 2012 IEEE computer society conference on computer vision and pattern recognition workshops (pp. 117-123). IEEE.
  26. Dias, T., Vitorino, J., Maia, E., Sousa, O., & Praça, I. (2023). KeyRecs: A keystroke dynamics and typing pattern recognition dataset. Data in Brief, 50, Article 109509.
  27. González, N., & Calot, E. (2022). Dataset of human-written and synthesized samples of free-text keystroke dynamics to evaluate liveness detection methods. Mendeley Data, 2, 2022.
  28. Hussain, F. (2023). IoT healthcare security dataset. Kaggle. https://www.kaggle.com/datasets/faisalmalik/iot-healthcare-security-dataset
  29. Ibrahim, A., Kadhim, A. F., Hamzah, A. E., & Al-Shareeda, M. A. (2026). A secure and scalable IoT home automation architecture with web and biometric control. International Journal of Cybersecurity Engineering and Innovation, 2026(1).
  30. Alshinwan, M., Memon, A. G., Ghanem, M. C., & Almaayah, M. (2025). Unsupervised text feature selection approach based on improved Prairie dog algorithm for text clustering. Jordanian Journal of Informatics and Computing, 2025(1), 27–36. https://doi.org/10.63180/jjic.thestap.2025.1.4
  31. Almarshood, R., & Rahman, M. M. H. (2025). Enhancing intrusion detection systems by using machine learning in smart cities: Issues, challenges and future research direction. STAP Journal of Security Risk Management, 2025(1), 3–21. https://doi.org/10.63180/jsrm.thestap.2025.1.1
  32. Alsahaim, S., Almaiah, M. A., & Sulaiman, R. B. (2023). Security threats in mobile phones: Challenges, countermeasures, and the importance of user awareness. International Journal of Cybersecurity Engineering and Innovation, 2023(1).
SCImago Journal & Country Rank