Context-aware adaptive routing framework for resource-efficient deepfake-aware biometric authentication
Authors
-
Huynh Ky Que
University of Economics Ho Chi Minh City, Ho Chi Minh City, Vietnamhttps://orcid.org/0009-0002-0821-6853
- Trinh Le Duy duytl@ueh.edu.vn
Department of Student Affairs, University of Economics Ho Chi Minh City, Vietnamhttps://orcid.org/0009-0001-3717-7921DOI:
10.46223/HCMCOUJS.tech.en.16.3.5983.2026Keywords:
deepfake detection; biometric security; context-aware authentication; risk-based authentication (RBA); adaptive systems; lightweight security; explainable AIAbstract
Deepfakes pose a significant risk to facial biometric identity verification systems. While modern detection models are precise, they require a lot of computing power. This can slow down real-time performance if used consistently for every login attempt. This paper suggests a context-aware adaptive authentication framework. It employs a lightweight Random Forest classifier to route login requests based on the estimated risk level. In this study, the deepfake detection is modelled with a simulation-based cost model rather than a fully implemented end-to-end detection system, allowing the proposed routing mechanism to be evaluated independently of any specific deepfake detection architecture. Experiments conducted on the risk-based authentication (RBA) dataset demonstrate that the proposed approach achieves high security performance, with a Recall of 99.22% and a false negative rate (FNR) below 1%. Additionally, the method enhances system efficiency, reducing computing cost by 57.68%, energy consumption by 58.48%, and processing latency by 62.42% compared to an Always-heavy baseline. These results indicate that integrating context-aware risk assessment into biometric pipelines offers a practical solution for balancing strong security with resource efficiency in real-world deployments.
Downloads
Download data is not yet available.References
Akhtar, Z. (2023). Deepfakes generation and detection: A short survey. Journal of Imaging, 9(1), Article 18. https://doi.org/10.3390/jimaging9010018
Ayeswarya, S., & Singh, K. J. (2025). Enhancing security and usability with context-aware multi-biometric fusion for continuous user authentication. Scientific Reports, 15, Article 30627. https://doi.org/10.1038/s41598-025-14833-z
Baseri, Y., Hafid, A. S., Makrakis, D., & Fereidouni, H. (2025). Privacy-preserving federated learning framework for risk-based adaptive authentication. arXiv. https://doi.org/10.48550/arXiv.2508.18453
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
DasGroup. (2022). Login data set for risk-based authentication [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6782156
Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv. https://doi.org/10.48550/arXiv.1702.08608
Fereidouni, H., Hafid, A. S., Makrakis, D., & Baseri, Y. (2024). F-RBA: A federated learning-based framework for risk-based authentication. arXiv. https://doi.org/10.48550/arXiv.2412.12324
Genuer, R., Poggi, J. M., & Tuleau-Malot, C. (2010). Variable selection using random forests. Pattern Recognition Letters, 31(14), 2225-2236. https://doi.org/10.1016/j.patrec.2010.03.014
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courvile, A. C., & Bengio, Y. (2014). Generative adversarial nets. In Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, & K. Q. Weinberger (Eds.), Advances in neural information processing systems 27 (pp. 2672-2680). Curran Associates. https://proceedings.neurips.cc/paper_files/paper/2014/hash/f033ed80deb0234979a61f95710dbe25-Abstract.html
Gorthi, N., Thakral, K., Ranjan, R., Singh, R., & Vatsa, M. (2025). LitMAS: A lightweight and generalized multi-modal anti-spoofing framework for biometric security. In Proceedings of Interspeech 2025 (pp. 5658-5662). ISCA. https://doi.org/10.21437/Interspeech.2025-2677
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer. https://doi.org/10.1007/978-0-387-84858-7
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv. https://doi.org/10.48550/arXiv.1704.04861
Kairouz, P., McMahan, H. B., Avent, B., Bellet, A., Bennis, M., Bhagoji, A. N., Bonawitz, K., Charles, Z., Cormode, G., & Cummings, R. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1-2), 1-210. https://doi.org/10.1561/2200000083
Khan, F. A., & Khan, M. K. (2025). Generative AI and deepfake detection in biometric systems. Cognitive Computation, 17(3), Article 112. https://doi.org/10.1007/s12559-025-10469-3
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S. I. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1), 56-67. https://doi.org/10.1038/s42256-019-0138-9
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, V. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems 30 (pp. 4765-4774). Curran Associates. https://arxiv.org/abs/1705.07874
MarketsandMarkets. (2025). Biometric system market: Global forecast to 2030. https://www.marketsandmarkets.com/PressReleases/biometric-technologies.asp
Molnar, C. (2022). Interpretable machine learning: A guide for making black box models explainable (2nd ed.). Christoph Molnar. https://christophm.github.io/interpretable-ml-book
Nguyen, T. T., Nguyen, Q. V. H., Nguyen, D. T., Nguyen, D. T., Huynh, T. T., Nahavandi, S., Nguyen, T. T., Pham, Q. V., & Nguyen, C. M. (2022). Deep learning for deepfakes creation and detection: A survey. Computer Vision and Image Understanding, 223, Article 103525. https://doi.org/10.1016/j.cviu.2022.103525
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12(85), 2825-2830.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). Why should I trust you? Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144). ACM. https://doi.org/10.1145/2939672.2939778
Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2019). FaceForensics++: Learning to detect manipulated facial images. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV 2019) (pp. 1-11). https://doi.org/10.1109/ICCV.2019.00009
Sohail, S., Sajjad, S. M., Zafar, A., Iqbal, Z., Muhammad, Z., & Kazim, M. (2025). Deepfake image forensics for privacy protection and authenticity using deep learning. Computers, 14(6), Article 225. https://doi.org/10.3390/computers14060225
Verdoliva, L. (2020). Media forensics and deepfake detection: A survey. IEEE Journal of Selected Topics in Signal Processing, 14(5), 910-932. https://doi.org/10.1109/JSTSP.2020.3002101
Wiefling, S., Dürmuth, M., & Lo Iacono, L. (2021). What’s in score for website users: A data-driven long-term study on risk-based authentication characteristics. In N. Borisov & C. Diaz (Eds.), Financial cryptography and data security (pp. 361-381). Springer. https://doi.org/10.1007/978-3-662-64331-0_19
Wiefling, S., Jørgensen, P. R., Thunem, S., & Lo Iacono, L. (2023). Pump up password security! Evaluating and enhancing risk-based authentication on a real-world large-scale online service. ACM Transactions on Privacy and Security, 26(1), Article 6. https://doi.org/10.1145/3546069
Downloads
Received: 28-05-2026Accepted: 28-08-2026Published: 09-10-2026Statistics
Abstract: 94 PDF: 85
FWCI: ---How to Cite
Huynh, K. Q., & Trinh, L. D. (2026). Context-aware adaptive routing framework for resource-efficient deepfake-aware biometric authentication. Ho Chi Minh City Open University Journal of Science - Engineering and Technology, 16(3), 34–54. https://doi.org/10.46223/HCMCOUJS.tech.en.16.3.5983.2026License
Copyright (c) 2026 Huynh Ky Que; Trinh Le Duy

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Similar Articles
- Nguyen Khanh Nhan, Duong Huu Thanh, Enhancing tomato leaf disease detection with contrast-limited adaptive histogram equalization and image blending for improved machine learning accuracy , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 16(1)2026
- Truong Kim Phuong, Lao Duc Thuan, Le Huyen Ai Thuy, DNA hypermethylation patterns of APC gene promoter in Vietnamese high-risk HPV infected patients , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 6 (1) 2016
- Nga Thi Nguyen, Thanh Thi Ngoc Nguyen, Hue Thi Nguyen, Association of SNP Rs34678647 with breast cancer risk in the Vietnamese population: An initial study , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 15(2)2025
- Hong Thi Thu Phan, Vuong Luong Nguyen, Trinh Quoc Vo, Nguyen Ho Trong Pham, Hybrid knowledge-infused collaborative filtering for enhanced movie clustering and recommendation , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 14(1)2024
- Phung Truong, A sum rate maximization problem in uplink MIMO with RSMA systems , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 14(1)2024
- Alfi Sophian, Ratna Purwaningsih, Authentication test of seasoning food materials made from turmeric using real-time PCR , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 13(2)2023
- Vo Thi Hong Tuyet, Edge detection based on augmented lagrangian method for lowquality medical images , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 8 (1) 2018
- Thai Hoang Chien, Nguyen Xuan Hung, Nguyen Thoi Trung, A locking-free quadratic nurbs-based isogeometric formulation for plates analysis , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 2 (1) 2012
- Guilbert Nicanor Abiera Atillo, Urban mobility analysis of megacity New York using density-based clustering techniques , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 16(3)2026 - SPECIAL ISSUE 20th ANNIVERSARY
- Tran Vinh Loc, Phan Dao Hoang Hiep, Nguyen Xuan Hung, Thermal buckling analysis of laminated composite plates using edge-based smoothed discrete shear gap method , Ho Chi Minh City Open University Journal of Science - Engineering and Technology: 2 (1) 2012
You may also start an advanced similarity search for this article.
- Trinh Le Duy duytl@ueh.edu.vn
