FaceLinkGen: Rethinking Identity Leakage in Privacy-Preserving Face Recognition with Identity Extraction

TL;DR

This paper introduces FaceLinkGen, an attack that links and regenerates faces from privacy-preserving templates, revealing that current pixel-based metrics underestimate privacy risks in face recognition systems.

Contribution

FaceLinkGen demonstrates high accuracy in identity matching and face regeneration from protected templates, exposing limitations of existing privacy evaluation methods.

Findings

FaceLinkGen achieves over 98.5% matching accuracy on recent PPFR systems.

FaceLinkGen attains above 96% face regeneration success rate.

Visual obfuscation does not effectively prevent identity exposure to intruders and service providers.

Abstract

Transformation-based privacy-preserving face recognition (PPFR) aims to verify identities while hiding facial data from attackers and malicious service providers. Existing evaluations mostly treat privacy as resistance to pixel-level reconstruction, measured by PSNR and SSIM. We show that this reconstruction-centric view fails. We present FaceLinkGen, an identity extraction attack that performs linkage/matching and face regeneration directly from protected templates without recovering original pixels. On three recent PPFR systems, FaceLinkGen reaches over 98.5\% matching accuracy and above 96\% regeneration success, and still exceeds 92\% matching and 94\% regeneration in a near zero knowledge setting. These results expose a structural gap between pixel distortion metrics, which are widely used in PPFR evaluation, and real privacy. We show that visual obfuscation leaves identity information broadly exposed to both external intruders and untrusted service providers.