1. SISN
  2. All Volumes and Issues
  3. Volume 18 (Part 2), 2025
  4. Adaptive Continuous Authentication System Based on the User's Emotional and Contextual State

Adaptive Continuous Authentication System Based on the User's Emotional and Contextual State

SISN.
2025;
Volume 18
: pp. 15 - 29
Authors:
  1. Nazar Oleksiv
  2. Mariia Nazarkevych
1
Lviv Polytechnic National University Department of Information Systems and Networks, Ukraine
2
Lviv Polytechnic National University Department of Information Systems and Networks, Ukraine

This article addresses the problem of low accuracy in continuous authentication systems caused by the natural variability of user behavior. An analysis of existing biometric approaches is conducted, justifying the selection of an adaptive two-stage model as an effective method for accounting for the user's psycho-emotional state. The authors designed the AURA (Automatic User Recognition Agent) system using a component-based approach, which allowed for a clear separation of the state identification and authentication tasks. A system architecture based on an ensemble of machine learning models was developed, which includes a State Probability Estimator (SPE) and a Core Authenticator (CA) that provide context-dependent verification. The proposed system demonstrated high training efficiency (91 %) and a low average Equal Error Rate (EER) across all users and states (5.7 %). These research results demonstrate the significant potential of the adaptive system to adapt to changes in user behavior and state depending on external and internal factors.

continuous authentication
behavioral biometrics
context-aware security
AURA
Adaptive User Recognition Agent
deep learning
  1. Ackerson, J. M., Dave, R., & Seliya, N. (2021). Applications of Recurrent Neural Network for Biometric Authentication & Anomaly Detection. Information, 12(7), 272. https://doi.org/10.3390/info12070272.
  2. Bentéjac, C., Csörgő, A., & Martínez-Muñoz, G. (2020). A Comparative Analysis of Gradient Boosting Algorithms. Artificial Intelligence Review, 54(3). https://doi.org/10.1007/s10462-020-09896-5.
  3. EDO, O. C., Tenebe, T., Etu, E., Ayuwu, A., Emakhu, J., & Adebiyi, S. (2022). Zero Trust Architecture: Trend and Impact on Information Security. International Journal of Emerging Technology and Advanced Engineering, 12(7), 140–147. https://doi.org/10.46338/ijetae0722_15.
  4. Gao, B., & Pavel, L. (2018). On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learning. https://doi.org/10.48550/arXiv.1704.00805.
  5. Kai, H., An, X., Enhua, W., Jianyuan, G., Chunjing, X., & Yunhe, W. (2021). Transformer in Transformer. Advances in Neural Information Processing Systems, 34. https://proceedings.neurips.cc/paper/2021/hash/ 854d9fca60b4bd07f9bb215d59ef5561-Abstract.html.
  6. Kozma, L., & Voderholzer, J. (2024). Theoretical Analysis of Byte-Pair Encoding. https://arxiv.org/abs/2411.08671.
  7. Kyurkchiev, N., & Markov, S. (2015). Sigmoid functions: some approximation and modelling aspects. LAP LAMBERT Academic Publishing, Saarbrucken, 4, 34.
  8. Nakano, M., Takahashi, A., & Takahashi, S. (2017). Generalized exponential moving average (EMA) model with particle filtering and anomaly detection. Expert Systems with Applications, 73, 187–200. https://doi.org/10.1016/j.eswa.2016.12.034.
  9. Qiao, M., Zhai, Y., & Wang, Y. (2025). Contrastive Learning for Continuous Touch-Based Authentication. https://doi.org/10.48550/arXiv.2504.17271.
  10. Senerath, D., Tharinda, S., Vishwajith, M., Rasnayaka, S., Wickramanayake, S., & Meedeniya, D. (2023). BehaveFormer: A Framework with Spatio-Temporal Dual Attention Transformers for IMU enhanced Keystroke Dynamics. https://doi.org/10.48550/arXiv.2307.11000.
  11. 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. https://doi.org/10.1007/s00521-024-10140-2.
  12. Swimpy Pahuja, & Goel, N. (2024). Multimodal biometric authentication: A review. AI Communications, 1–23. https://doi.org/10.3233/aic-220247.
  13. Wang, C., Xiao, Y., Gao, X., Li, L., & Wang, J. (2023). A Framework for Behavioral Biometric Authentication Using Deep Metric Learning on Mobile Devices. IEEE Transactions on Mobile Computing, 22(1), 19–36. https://doi.org/10.1109/tmc.2021.3072608.
  14. Xue, J., Huang, Q., Wu, S., & Nagao, T. (2022). LSTM-Autoencoder Network for the Detection of Seismic Electric Signals. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–12. https://doi.org/10.1109/tgrs.2022.3183389.
  15. Yang, K., Kpotufe, S., & Feamster, N. (2021). An Efficient One-Class SVM for Anomaly Detection in the Internet of Things. https://doi.org/10.48550/arXiv.2104.11146.
  16. Zhang, G., Bortoletto, M., Hu, Z., Shi, L., Bâce, M., & Bulling, A. (2023). Exploring Natural Language Processing Methods for Interactive Behaviour Modelling. https://doi.org/10.48550/arXiv.2303.16039.
  17. Zhang, G., Hu, Z., Bâce, M., & Bulling, A. (2024). Mouse2Vec: Learning Reusable Semantic Representations of Mouse Behaviour. Proceedings of the CHI Conference on Human Factors in Computing Systems, 1–17. https://doi.org/10.1145/3613904.3642141.