LBFTI: Layer-Based Facial Template Inversion for Identity-Preserving Fine-Grained Face Reconstruction

2026-04-20

AI Summary

This work addresses the privacy risks associated with template inversion in face-based identity verification by proposing a hierarchical face template inversion method. The approach decomposes a face into three layers—foreground (facial landmarks), midground (skin texture), and background—and integrates a layered generative adversarial network with a three-stage training strategy: independent generation, fusion-based reconstruction, and joint fine-tuning. A secondary template feature injection mechanism further enhances fidelity while preserving identity consistency. Experimental results demonstrate that the proposed method improves True Acceptance Rate (TAR) by 25.3% under machine-based verification and significantly outperforms existing approaches in perceptual similarity, as validated by both quantitative metrics and user studies.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Machine Learning: Privacy
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

In face recognition systems, facial templates are widely adopted for identity authentication due to their compliance with the data minimization principle. However, facial template inversion technologies have posed a severe privacy leakage risk by enabling face reconstruction from templates. This paper proposes a Layer-Based Facial Template Inversion (LBFTI) method to reconstruct identity-preserving fine-grained face images. Our scheme decomposes face images into three layers: foreground layers (including eyebrows, eyes, nose, and mouth), midground layers (skin), and background layers (other parts). LBFTI leverages dedicated generators to produce these layers, adopting a rigorous three-stage training strategy: (1) independent refined generation of foreground and midground layers, (2) fusion of foreground and midground layers with template secondary injection to produce complete panoramic face images with background layers, and (3) joint fine-tuning of all modules to optimize inter-layer coordination and identity consistency. Experiments demonstrate that our LBFTI not only outperforms state-of-the-art methods in machine authentication performance, with a 25.3% improvement in TAR, but also achieves better similarity in human perception, as validated by both quantitative metrics and a questionnaire survey.

Problem

• facial template inversion
• privacy leakage
• identity-preserving
• face reconstruction
• fine-grained

Innovation

• layer-based inversion
• facial template inversion
• identity-preserving reconstruction
• fine-grained face generation
• three-stage training