Security Analysis on Face Biometric Authentication Under Different AI-Manipulated Face

Fathimah Hasanti; Nurul Ilmi; Desi Nurnaningsih

doi:10.58477/cj.v4i2.503

Articles Vol. 4, No. 2 (2026)

Fathimah Hasanti

, Nurul Ilmi

, Desi Nurnaningsih

Telkom University

10.58477/cj.v4i2.503 Published: 2026-08-30

Abstract

The rapid evolution of Generative Artificial Intelligence (Gen AI) has enabled realistic facial manipulation using AI-generated images, creating serious security threats to face biometric authentication systems. Previous studies have mainly focused on deepfake detection and face recognition improvement, while limited attention has been given to the effects of AI-based facial manipulation on biometric authentication security. This study examines the vulnerability of face biometric authentication to various Gen AI-powered facial manipulation attacks. FaceForensics++ was used to create verification pairs consisting of genuine, impostor, and manipulated faces. ArcFace generated face embeddings, while cosine similarity measured identity similarity between faces. Equal Error Rate (EER) was used to determine the authentication threshold. The threshold was then applied to evaluate DeepFakes, FaceSwap, Face2Face, NeuralTextures, and FaceShifter using False Acceptance Rate (FAR), False Rejection Rate (FRR), EER, and cosine similarity scores. The results indicate different authentication behaviors among manipulation algorithms. Face2Face and NeuralTextures produced higher FAR and similarity scores, indicating greater ability to retain identity information.

Keywords:

AI-Manipulated Authentication Face Biometric Facial Manipulation Security

How to Cite

Hasanti, F., Ilmi, N., & Nurnaningsih, D. (2026). Security Analysis on Face Biometric Authentication Under Different AI-Manipulated Face. Computer Journal, 4(2), 304-311. https://doi.org/10.58477/cj.v4i2.503

Fathimah Hasanti

Telkom University

Department of Information Technology, Jakarta Campus Directorate, Universitas Telkom, West Jakarta City, Special Capital Region of Jakarta, Indonesia.

Nurul Ilmi

Telkom University

Department of Information Technology, Jakarta Campus Directorate, Universitas Telkom, West Jakarta City, Special Capital Region of Jakarta, Indonesia.

Desi Nurnaningsih

Telkom University

Department of Information Technology, Jakarta Campus Directorate, Universitas Telkom, West Jakarta City, Special Capital Region of Jakarta, Indonesia.

DOI	https://doi.org/10.58477/cj.v4i2.503
Publication Date	2026-08-30
Journal Section	Articles

Castro, F., Gattulli, V., Impedovo, D., & Monaco, A. (2026). DeepDect: An explainable AI platform for face swapping and face generation DeepFake detection. Multimedia Tools and Applications, 85, Article 500. https://doi.org/10.1007/s11042-026-21672-1
Fitzmaurice, D., & O’Brien, O. (2025). Generative AI deepfakes: Real-world threats to facial biometric authentication. In 2025 Cyber Research Conference–Ireland (Cyber-RCI). https://doi.org/10.1109/cyber-rci68134.2025.11385234
Gore, S., Shaikh, N., Sandeep, K. S., Jagadish, S., Priya, L., & Priyanka, T. P. (2025). Next-gen biometric security: AI for identity authentication. In 2025 6th International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 2205–2212). IEEE. https://doi.org/10.1109/ICESC65114.2025.11212442
He, S., Lei, Y., Zhang, Z., Sun, Y., Li, S., Zhang, C., & Ye, J. (2025). Identity deepfake threats to biometric authentication systems: Public and expert perspectives. arXiv. https://doi.org/10.48550/arXiv.2506.06825
Holstein, D. (2024). Analysis of attack methods with artificial intelligence [Bachelor’s thesis, Esslingen University]. https://doi.org/10.13140/RG.2.2.23071.06566
Khaund, B. (2025). AI and identity security: The threat of deepfakes and the future of authentication. World Journal of Advanced Engineering Technology and Sciences, 15(3), 2094–2101. https://doi.org/10.30574/wjaets.2025.15.3.1135
Al Kishri, W., Yousif, J. H., Al Bahri, M., Zakarya, M., Khan, N., Al Maskari, S. S., & Gurhanli, A. (2025). A comparative study of deepfake facial manipulation technique using generative adversarial networks. Discover Artificial Intelligence, 5(1), Article 109. https://doi.org/10.1007/s44163-025-00337-2
Krantz, T., & Jonker, A. (2026, May 14). What is cosine similarity? IBM. https://www.ibm.com/think/topics/cosine-similarity
Lin, C., Chen, F., Ng, H., & Lin, W. (2023). Invisible adversarial attacks on deep learning-based face recognition models. IEEE Access, 11, 51567–51577. https://doi.org/10.1109/ACCESS.2023.3279488
Maaref, Z., Belhadj, F., Attia, A., Akhtar, Z., Jasser, M. B., Ramly, A. M., & Mohamed, A. W. (2024). A comprehensive review of vulnerabilities and attack strategies in cancelable biometric systems. Egyptian Informatics Journal, 27, Article 100511. https://doi.org/10.1016/j.eij.2024.100511
Masood, M., Nawaz, M., Malik, K. M., Javed, A., Irtaza, A., & Malik, H. (2023). Deepfakes generation and detection: State-of-the-art, open challenges, countermeasures, and way forward. Applied Intelligence, 53(4), 3974–4026. https://doi.org/10.1007/s10489-022-03766-z
Naik, D., Inamdar, A., & Sonawane, Y. (2025). Fake media forensics: AI-driven forensic analysis of fake multimedia content. International Journal of Scientific Research in Engineering and Management, 9(5), 1–9. https://doi.org/10.55041/IJSREM47208
Patel, J., & Musale, V. (2025). Automated AI-powered intrusion detection system (IDS), biometric authentication and deepfake detection. In Proceedings of the International Conference on Computational Complexity and Intelligent Algorithms (pp. 663–676). Springer. https://doi.org/10.1007/978-981-96-7473-2_49
Ren, M., Wang, Y., Zhu, Y., Huang, Y., Sun, Z., Li, Q., & Tan, T. (2024). Artificial immune system of secure face recognition against adversarial attacks. International Journal of Computer Vision, 132(12), 5718–5740. https://doi.org/10.1007/s11263-024-02153-0
Sheikh, B. U. H., & Zafar, A. (2024). Beyond accuracy and precision: A robust deep learning framework to enhance the resilience of face mask detection models against adversarial attacks. Evolving Systems, 15(1), 1–24. https://doi.org/10.1007/s12530-023-09522-z
Sonkusare, M. G., Meshram, H. A., Sah, A., & Prakash, S. (2022). Detection and verification for deepfake bypassed facial feature authentication. In 2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS) (pp. 646–649). IEEE. https://doi.org/10.1109/ICAIS53314.2022.9742980
Tariq, S., Jeon, S., & Woo, S. S. (2022). Am I a real or fake celebrity? Evaluating face recognition and verification APIs under deepfake impersonation attack. In Proceedings of the ACM Web Conference 2022 (pp. 512–523). ACM. https://doi.org/10.1145/3485447.3512212
Tolosana, R., Romero-Tapiador, S., Vera-Rodriguez, R., Gonzalez-Sosa, E., & Fierrez, J. (2022). DeepFakes detection across generations: Analysis of facial regions, fusion, and performance evaluation. Engineering Applications of Artificial Intelligence, 110, Article 104673. https://doi.org/10.1016/j.engappai.2022.104673
Vakhshiteh, F., Nickabadi, A., & Ramachandra, R. (2021). Adversarial attacks against face recognition: A comprehensive study. IEEE Access, 9, 92735–92756. https://doi.org/10.1109/ACCESS.2021.3092646
Verma, S. (2025). Synthetic identities and deepfake attacks: The next frontier in enterprise AI security. European Modern Studies Journal, 9(5), 176–189. https://doi.org/10.59573/emsj.9(5).2025.17
Zhalgas, A., Amirgaliyev, B., & Sovet, A. (2025). Robust face recognition under challenging conditions: A comprehensive review of deep learning methods and challenges. Applied Sciences, 15(17), Article 9390. https://doi.org/10.3390/app15179390