Adaptive defence model of remote identity verification systems against deepfake and voice cloning attacks: the case of government and financial digital services
Keywords:
deepfake, injection attack, voice cloning, digital identification, risk assessment, artificial intelligenceAbstract
Generative artificial intelligence enables the real-time imitation of faces and voices, giving rise to new types of attacks on remote identity verification systems. The article analyses the weak points of the biometric verification process used in government and financial digital services and proposes an adaptive defence model that jointly assesses deepfake, voice cloning and camera-stream fake-content injection (injection) attacks. The model combines five kinds of signals (channel integrity, face, voice, document and data consistency, behaviour) into a single risk indicator, takes the criticality of the operation into account, raises the risk when trustworthy signals are lacking, and selects the verification step according to the result. It is proposed to determine the signal weights through expert assessment using Saaty’s analytic hierarchy process. According to the analysed sources, detectors that showed high accuracy on laboratory data deteriorate significantly on real-world deepfakes, so relying on a single detector is not sufficient. Using Uzbekistan as an example, directions for implementing the model are indicated from the standpoint of the OneID and MyID systems and the laws on personal data and cybersecurity. The model is conceptual in nature; experimental verification is presented as an evaluation plan for the next stage
References
1. ENISA. (2025). ENISA threat landscape 2025. European Union Agency for Cybersecurity.
2. Financial Crimes Enforcement Network. (2024). FinCEN alert on fraud schemes involving deepfake media targeting financial institutions (FIN-2024-Alert004). U.S. Department of the Treasury. https://www.fincen.gov/sites/default/files/shared/FinCEN-Alert-DeepFakes-Alert508FINAL.pdf
3. Europol. (2022). Facing reality? Law enforcement and the challenge of deepfakes. Publications Office of the European Union. https://www.europol.europa.eu/publications-events/publications/facing-reality-law-enforcement-and-challenge-of-deepfakes
4. Temoshok, D., Proud-Madruga, D., Choong, Y.-Y., Galluzzo, R., Gupta, S., LaSalle, C., Lefkovitz, N., & Regenscheid, A. (2025). Digital identity guidelines (NIST Special Publication 800-63-4). National Institute of Standards and Technology. https://doi.org/10.6028/NIST.SP.800-63-4
5. Saaty, T. L. (2008). Decision making with the analytic hierarchy process. International Journal of Services Sciences, 1(1), 83–98.
6. International Organization for Standardization & International Electrotechnical Commission. (2023). Information technology — Biometric presentation attack detection — Part 3: Testing and reporting (ISO/IEC 30107-3:2023). https://www.iso.org/standard/79520.html
7. European Committee for Standardization. (2024). Biometric data injection attack detection (CEN/TS 18099:2024).
8. Wang, X., Delgado, H., Tak, H., Jung, J.-W., Shim, H.-J., Todisco, M., Kukanov, I., Liu, X., Sahidullah, M., Kinnunen, T., Evans, N., et al. (2026). ASVspoof 5: Design, collection and validation of resources for spoofing, deepfake, and adversarial attack detection using crowdsourced speech. Computer Speech & Language, 95, 101825. https://doi.org/10.1016/j.csl.2025.101825
9. Tolosana, R., Vera-Rodriguez, R., Fierrez, J., Morales, A., & Ortega-Garcia, J. (2020). DeepFakes and beyond: A survey of face manipulation and fake detection. Information Fusion, 64, 131–148. https://doi.org/10.1016/j.inffus.2020.06.014
10. Mirsky, Y., & Lee, W. (2021). The creation and detection of deepfakes: A survey. ACM Computing Surveys, 54(1), Article 7. https://doi.org/10.1145/3425780
11. Rössler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2019). FaceForensics++: Learning to detect manipulated facial images. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.48550/arXiv.1901.08971
12. Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., & Canton Ferrer, C. (2020). The DeepFake Detection Challenge (DFDC) dataset (arXiv:2006.07397). https://doi.org/10.48550/arXiv.2006.07397
13. Chandra, N. A., Murtfeldt, R., Qiu, L., Karmakar, A., Lee, H., Tanumihardja, E., Farhat, K., Caffee, B., Paik, S., Lee, C., Choi, J., Kim, A., & Etzioni, O. (2025). Deepfake-Eval-2024: A multi-modal in-the-wild benchmark of deepfakes circulated in 2024 (arXiv:2503.02857). https://doi.org/10.48550/arXiv.2503.02857
14. European Parliament & Council of the European Union. (2024). Regulation (EU) 2024/1689 laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). Official Journal of the European Union.
15. Financial Action Task Force. (2020). Guidance on digital identity. FATF/OECD. https://www.fatf-gafi.org/media/fatf/documents/recommendations/pdfs/Guidance-on-Digital-Identity-report.pdf
16. National Statistics Committee of the Republic of Uzbekistan. (2025). [Share of the population using the Internet, January–August 2025]. https://stat.uz/en/press-center/news-of-committee/64213-zbekiston-a-olisining-94-2-foizi-internetdan-fojdalanadi-4
17. President of the Republic of Uzbekistan. (2020). On measures to approve the “Digital Uzbekistan — 2030” strategy and ensure its effective implementation (Decree No. PF-6079, 5 October 2020).
18. dgov.uz. (n.d.). Unified identification system (OneID). https://dgov.uz/en/identification/
19. MyID. (n.d.). MyID — biometric identification system. https://myid.uz/en/
20. Republic of Uzbekistan. (2019). On personal data (Law No. ZRU-547, 2 July 2019).
21. Republic of Uzbekistan. (2022). On cybersecurity (Law No. ZRU-764, 15 April 2022). https://lex.uz/en/docs/6997403
22. Nurmakhamad M., Aliqosimova M., Model for improving shipment management efficiency by integrating artificial intelligence and iot technologies inthe postal-logistics system. "Descendants of Al-Farghani" electronic scientific journal. ISSN 2181-4252. Vol: 1| Iss: 3 | 2026 year. рр 524-531.

