On Generating Identifiable Virtual Faces

TL;DR

This paper introduces a novel method for generating virtual face images that are visually different from the original but still identifiable, balancing privacy protection with face recognition utility.

Contribution

We propose the IVFG model that creates virtual faces with new identities using a user-specific key, employing multi-task learning and triplet training for identifiability.

Findings

Effective virtual face generation with identifiable features

High recognition accuracy across multiple face datasets

Preserves privacy while maintaining utility

Abstract

Face anonymization with generative models have become increasingly prevalent since they sanitize private information by generating virtual face images, ensuring both privacy and image utility. Such virtual face images are usually not identifiable after the removal or protection of the original identity. In this paper, we formalize and tackle the problem of generating identifiable virtual face images. Our virtual face images are visually different from the original ones for privacy protection. In addition, they are bound with new virtual identities, which can be directly used for face recognition. We propose an Identifiable Virtual Face Generator (IVFG) to generate the virtual face images. The IVFG projects the latent vectors of the original face images into virtual ones according to a user specific key, based on which the virtual face images are generated. To make the virtual face images identifiable, we propose a multi-task learning objective as well as a triplet styled training strategy to learn the IVFG. We evaluate the performance of our virtual face images using different face recognizers on diffident face image datasets, all of which demonstrate the effectiveness of the IVFG for generate identifiable virtual face images.