Abstract
The problem of detecting falsifications involving digital facial images is examined as a challenge to modern document security systems in the context of biometric identification and verification. A set of relevant measures aimed at dealing with this issue is proposed. In the context of the widespread implementation of automated biometric identification and verification systems in developed countries, manipulation of digital facial images (morphing) represents a relatively new challenge, particularly for automated border control systems, where both digital and printed facial images of the document holder are used for identification. Modern face-recognition systems with a high degree of probability recognize facial images generated through digital manipulation as authentic. At the same time, as developed countries actively implement high-tech solutions into the activities of law enforcement and migration services, it is correct to claim about the global trend toward the gradual replacement of direct human involvement in document verification process with automated systems. Therefore, the problem of detecting altered facial images in identity documents requires comprehensive solutions encompassing organizational, law enforcement, technical and ethical spheres. In the field of forensic science, modern challenges arising in the era of widespread digitalization require the modernization of existing methods and the development of new approaches in facialrecognition derived from physical images. These approaches should take into account biometric identification methods and the implementation of artificial intelligence technologies in forensic examination to minimize the probability of expert mistakes.
References
Androshchuk H.O. (2023). Shtuchnyi intelekt i intelektualna vlasnist: problemy rehuliuvannia: naukovo-praktychne vydannia [Artificial intelligence and intellectual property: regulatory issues: scientific and practical publication]. Naukovo-doslidnyi instytut intelektualnoi vlasnosti Natsionalnoi akademii pravovykh nauk Ukrainy. Kyiv: Interservice. 204 p. [in Ukrainian].
Havrylko D.D., Skakalina O.V. (2025). Metody vyiavlennia manipuliatsii u tsyfrovykh zobrazhenniakh: tekhnichna veryfikatsiia yak instrument protydii dezinformatsii [Methods for detecting manipulation in digital images: technical verification as a tool for countering disinformation]. Zbirnyk materialiv 77-i naukovoi konferentsii profesoriv, vykladachiv, naukovykh pratsivnykiv, aspirantiv ta mahistrantiv universytetu, Natsionalnyi universytet “Poltavska politekhnika imeni Yuriia Kondratiuka”, Poltava, May 16–22, 2025, 534–536 [in Ukrainian].
Handbook of Computational Geometry / edited by J.-R. Sack, J. Urrutia. North Holland, 2000. P. 121–153. URL: https://www.sciencedirect.com/book/edited-volume/9780444825377/handbook-of-computational-geometry (accessed: 01.02.2026) [in English].
Filippov S. (2021). Okremi aspekty vykorystannia pasazhyrskykh danykh (API/PNR) v interesakh prykordonnoi bezpeky [Selected aspects of the use of passenger data (API/PNR) in the interests of border security]. Rule of Law, 43, 169–176. DOI: https://doi.org/10.18524/2411-2054.2021.43.240997 [in Ukrainian].
Scherhag U., Budhrani D., Gomez-Barrero M., Busch C. (2018). Detecting morphed face images using facial landmarks. Proceedings of the International Conference on Image and Signal Processing, Cherbourg, France, July 2–4, 2018, 444–452. URL: https://orbit.dtu.dk/en/publications/detecting-morphed-face-images-using-facial-landmarks/ (accessed: 29.01.2026) [in English].
SOTAMD. (n.d.). State of the art of Morphing Detection. URL: https://www.utwente.nl/en/eemcs/dmb/research/research-archive/sotamd/ (accessed: 02.01.2026) [in English].
Busch C., Caillebotte S., Seidel U., Knopjes F., Maltoni D., Ferrara M., Veldhuis R., Spreeuwers L., Raja K., Raghavendra R., Gomez-Barrero M., Rathgeb C. (2019). Face morphing attacks: what needs to be done. Proceedings of the International Conference on Biometrics for Borders, Frontex, Warsaw, October 9–10, 2019, 96–108. URL: https://www.christoph-busch.de/files/Busch-iMARS-Frontex-2019.pdf (accessed: 02.01.2026) [in English].
iMARS: official website. (n.d.). URL: https://imars-project.eu/concept-objectives/ (accessed: 03.02.2026) [in English].
Commission proposes an EU Digital Travel application. European Commission. (2024). URL: https://ec.europa.eu/commission/presscorner/detail/en/ip_24_5047 (accessed: 03.02.2026) [in English].
Informatsiia shchodo Yevropeiskoi systemy informatsii ta avtoryzatsii podorozhei (ETIAS) [Information on the European Travel Information and Authorisation System (ETIAS)]. Predstavnytstvo Yevropeiskoho Soiuzu v Ukraini: ofitsiinyi vebsait. URL: https://www.eeas.europa.eu/delegations/ukraine (accessed: 03.02.2026) [in Ukrainian].
Busch C. (2024). Challenges for automated face recognition systems. Nature Reviews Electrical Engineering. URL: https://www.christoph-busch.de/f iles/Busch-NatureReview-ChallengesFRS-2024.pdf (accessed: 04.02.2026) [in English].
Europol Innovation Lab. (2025). Biometric vulnerabilities: ensuring future law enforcement preparedness. An Observatory Report from the Europol Innovation Lab. Luxembourg: Publications Office of the European Union. 60 p. DOI: https://doi.org/10.2813/8081090 [in English].
Jacquet M., Champod C. (2020). Automated face recognition in forensic science: review and perspectives. Forensic Science International, 307, 110–124. DOI: https://doi.org/10.1016/j.forsciint.2019.110124 [in English].
O’Toole A.J., Castillo C.D. (2021). Face recognition by humans and machines: three fundamental advances from deep learning. Annual Review of Vision Science, 7, 543–570. DOI: https://doi.org/10.1146/annurev-vision-093019-111701[in English].
Phillips P.J., Yates A.N., Hu Y., Hahn C.A., Noyes E., Jackson K., Cavazos J.G., Jeckeln G., Ranjan R., Sankaranarayanan S., Chen J.-C., Castillo C.D., Chellappa R., White D., O’Toole A.J. (2018). Face recognition accuracy of forensic examiners, superrecognizers, and algorithms. Proceedings of the National Academy of Sciences, 115(24), 6171–6176. DOI: https://doi.org/10.1073/pnas.1721355115 [in English].
European Network of Forensic Science Institutes. (2022). Guideline for Facial Recognition System End Users. Version 1.0. 36 p. URL: https://enfsi.eu/wp-content/uploads/2022/07/GUIDELINES-FOR-FR-USERS-V_01_public-review-1-1.pdf (accessed: 04.02.2026) [in English].
European Network of Forensic Science Institutes. (2018). ENFSI Best Practice Manual for Facial Image Comparison (BPM-DI-01). 50 p. URL: https://enfsi.eu/wp-content/uploads/2017/06/ENFSI-BPM-DI-01.pdf (accessed: 05.02.2026) [in English].
Pereidenko A. (2025). Vykorystannia avtomatyzovanykh system dlia perevirky rezultativ analizu zobrazhen oblychchia [The use of automated systems for verifying the results of facial image analysis]. Aktualni pytannia sudovoi ekspertyzy, kryminolohii ta kryminalnoho protsesu: materialy VII Mizhnarodnoi naukovo-praktychnoi konferentsii, Kyiv, December 10, 2025 / za red. M.Ye. Kiselova. Kyiv: Lira-K, 273–276 [in Ukrainian].