Realistic Face Reconstruction from Facial Embeddings via Diffusion Models
Preprint
Abstract
With the advancement of face recognition (FR) systems, privacy-preserving face recognition (PPFR) systems have gained popularity for their accurate recognition, enhanced facial privacy protection, and robustness to various attacks. However, there are limited studies to further verify privacy risks by reconstructing realistic high-resolution face images from embeddings of these systems, especially for PPFR. In this work, we propose the face embedding mapping (FEM), a general framework that explores Kolmogorov-Arnold Network (KAN) for conducting the embedding-to-face attack by leveraging pre-trained Identity-Preserving diffusion model against state-of-the-art (SOTA) FR and PPFR systems. Based on extensive experiments, we verify that reconstructed faces can be used for accessing other real-word FR systems. Besides, the proposed method shows the robustness in reconstructing faces from the partial and protected face embeddings. Moreover, FEM can be utilized as a tool for evaluating safety of FR and PPFR systems in terms of privacy leakage. All images used in this work are from public datasets.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Toward a Privacy-Preserving Face Recognition System: A Survey of Leakages and SolutionsACM Computing Surveys, 2025
- Make Privacy Renewable! Generating Privacy-Preserving Faces Supporting Cancelable Biometric Recognition2024
- Vulnerability of State-of-the-Art Face Recognition Models to Template Inversion AttackIEEE Transactions on Information Forensics and Security, 2024
- GhostFaceNets: Lightweight Face Recognition Model From Cheap OperationsIEEE Access, 2023
- Towards Protecting Face Embeddings in Mobile Face Verification ScenariosIEEE Transactions on Biometrics, Behavior, and Identity Science, 2022
- MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices2018
- On the Reconstruction of Face Images from Deep Face TemplatesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Biohashing: two factor authentication featuring fingerprint data and tokenised random numberPattern Recognition, 2004