Template recovery attack on encrypted face recognition systems with unprotected decision using synthetic faces
Frontiers in Imaging · 2025
DOI: 10.3389/fimag.2025.1476377 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Imaging, 2025. Verfasst von Amina Bassit und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 Marie SkÅodowska-Curie Actions.
Abstract (Originalsprache)
Introduction
Homomorphic encryption (HE) enables privacy-preserving face recognition by allowing encrypted facial embeddings to be compared without decryption. While efficient, these systems often reveal comparison scores in plaintext, introducing a security risk. Revealing these scores can potentially allow adversaries to reconstruct sensitive facial embeddings and infer demographic attributes, thus compromising user privacy.
Methods
This work proposes a training-less face template recovery attack leveraging the Lagrange multiplier optimization method. The attack requires only a small set of randomly generated synthetic facial images and their associated comparison scores with a target template. The method assumes attackers use spoofed synthetic faces and lack direct access to the face recognition system, aligning with real-world threat models.
Results
Experimental evaluation demonstrates the feasibility and effectiveness of the proposed attack. It shows that between 50 and 192 comparison scores and synthetic images are sufficient to recover the target face template with 100% success under strict system thresholds. The recovered templates closely resemble the original and retain identifiable soft biometric traits.
Discussion
The findings reveal a critical vulnerability in face recognition systems employing inner product similarity measures under homomorphic encryption. Even without system access or training data, attackers can exploit leaked comparison scores to compromise facial privacy. The study underscores the need to reassess how score leakage is handled in encrypted recognition systems and explore stronger protection mechanisms against template reconstruction.
Förderung
- H2020 Marie SkÅodowska-Curie Actions
Zitieren
APA
Bassit, A., Hahn, F., Rezgui, Z., Shahreza, H. O., Veldhuis, R., & Peter, A. (2025). Template recovery attack on encrypted face recognition systems with unprotected decision using synthetic faces. Frontiers in Imaging. https://doi.org/10.3389/fimag.2025.1476377
Vancouver
Bassit A, Hahn F, Rezgui Z, Shahreza HO, Veldhuis R, Peter A. Template recovery attack on encrypted face recognition systems with unprotected decision using synthetic faces. Frontiers in Imaging. 2025. doi:10.3389/fimag.2025.1476377
BibTeX
@article{Bassit2025,
author = {Bassit, Amina and Hahn, Florian and Rezgui, Zohra and Shahreza, Hatef Otroshi and Veldhuis, Raymond and Peter, Andreas},
title = {Template recovery attack on encrypted face recognition systems with unprotected decision using synthetic faces},
journal = {Frontiers in Imaging},
year = {2025},
doi = {10.3389/fimag.2025.1476377}
}
EUVIMED