Enhancing Portal-Based Transaction Security Through an Optimized Adaptive Two-Factor Authentication Framework
Abstract
Conventional Two-Factor Authentication (2FA) systems typically employ static threshold parameters that do not adapt to evolving cyber threats, resulting in suboptimal trade-offs between security and usability. This paper presents an adaptive optimization framework that dynamically tunes 2FA thresholds using the Lion Optimization Algorithm (LOA). A Time-based One-Time Password (TOTP) authentication mechanism was integrated into a prototype transaction portal and evaluated under brute‑force and credential‑stuffing attack scenarios. Experimental simulations involving 1,000 authentication attempts showed that the static 2FA configuration achieved False Acceptance Rates (FAR) of 0.06 and 0.09 under brute‑force and credential‑stuffing attacks, respectively. In contrast, the LOA‑based adaptive framework reduced FAR to 0.01 for both attack types, increased the success rate to 0.99, reduced average authentication time from 0.42 s to 0.04 s, and maintained system reliability above 98%. These results demonstrate that metaheuristic optimization significantly enhances authentication robustness and usability, offering a scalable solution for securing portal‑based transaction systems.References
Adesoji, A., Etido, B., Oyebola, A., Fatade, O., & Adeoti, B. (2024). Design and implementation of an enhanced two-factor authentication model. Current Trends in Information Communication Technology Research (CTICTR), 3(1).
Bhanderi, D., Kavathiya, M., Bhut, T., Kaur, H., & Mehta, M. (2023). Impact of two-factor authentication on user convenience and security. In Proceedings of the 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 617–622).
Laube, A., & Koenig, R. (2017). Secure two-factor authentication with SwissPass Crypto Card: A case study. In Proceedings of the Future Technologies Conference (FTC) (pp. 837–844).
Meyer, L. A., Romero, S., Bertoli, G., Burt, T., Weinert, A., & Ferres, J. M. L. (2023). How effective is multifactor authentication at deterring cyberattacks? arXiv. https://arxiv.org/abs/2305.00945
Naqvi, K., Perova, K., Farooq, A., Makhdoom, I., Oyedeji, S., & Porras, J. (2023). Mitigation strategies against phishing attacks: A systematic literature review. Computers & Security, 132, 103387. https://doi.org/10.1016/j.cose.2023.103387
Otta, S. P., & Panda, S. (2023). A systematic survey of multi-factor authentication for cloud infrastructure. Future Internet, 15(4), 146. https://doi.org/10.3390/fi15040146
Picard, C., & Pierre, S. (2023). RLAuth: A risk-based authentication system using reinforcement learning. IEEE Access, 11, 61129–61143. https://doi.org/10.1109/ACCESS.2023.3286376
Rajakumar, B. R. (2012). The Lion's algorithm: A new nature-inspired search algorithm. Procedia Technology, 6, 126–135. https://doi.org/10.1016/j.protcy.2012.10.016
Soares, L. F. B., Fernandes, D. A. B., Freire, M. M., & Inácio, P. R. M. (2013). Secure user authentication in cloud computing management interfaces. In Proceedings of the 2013 IEEE 32nd International Performance Computing and Communications Conference (IPCCC). https://doi.org/10.1109/IPCCC.2013.6742763
Stoumpos, A. I., Kitsios, F., & Talias, M. A. (2023). Digital transformation in healthcare: Technology acceptance and its applications. International Journal of Environmental Research and Public Health, 20(4), 3407. https://doi.org/10.3390/ijerph20043407
Yusuf, S. M., Abdulrazaq, M. B., Yahaya, B., Haruna, Z., Ore-Ofe, A., Adegoke, A. S., Omogoye, S. O., & Salami, S. O. (2025). Anomaly detection in portal system networks: A hybrid EMLOA-OCSVM approach. European Scientific Journal, 21(24), 21–56. https://doi.org/10.19044/esj.2025.v21n24p21
Copyright (c) 2026 Oluwole O. Green, Adesoye S. Adegoke, Idris O. Olajuwon

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The authors hereby represent and warrant that the paper is original and that they are the authors of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. If in future any violation of any copyright come in notice, then the author will be responsible and not FUOYEJET.
The authors declare that:
- This paper has not been published in the same form elsewhere.
- It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
- A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.
Furthermore, the copyright after publication belongs to the Author(s) (for articles published in 2020 and beyond) and licensed under the creative commons license CC-BY-NC (http://creativecommons.org/licenses/by-nc/4.0). The copyright covers the right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.