Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Model

TL;DR

This paper introduces a novel method for reconstructing face images from face embeddings using a foundation model and an adapter, significantly improving attack effectiveness across various face recognition systems.

Contribution

The paper presents a new approach employing a foundation model and adapter to accurately reconstruct faces from embeddings, enhancing attack transferability and outperforming previous methods.

Findings

Reconstructed faces successfully attack multiple face recognition models.

The method outperforms previous face reconstruction attacks.

High transferability of reconstructed images across models.

Abstract

Face recognition systems extract embedding vectors from face images and use these embeddings to verify or identify individuals. Face reconstruction attack (also known as template inversion) refers to reconstructing face images from face embeddings and using the reconstructed face image to enter a face recognition system. In this paper, we propose to use a face foundation model to reconstruct face images from the embeddings of a blackbox face recognition model. The foundation model is trained with 42M images to generate face images from the facial embeddings of a fixed face recognition model. We propose to use an adapter to translate target embeddings into the embedding space of the foundation model. The generated images are evaluated on different face recognition models and different datasets, demonstrating the effectiveness of our method to translate embeddings of different face recognition models. We also evaluate the transferability of reconstructed face images when attacking different face recognition models. Our experimental results show that our reconstructed face images outperform previous reconstruction attacks against face recognition models.