A Systematical Solution for Face De-identification

TL;DR

This paper presents a comprehensive face de-identification system combining attribute disentanglement, face swapping, and adversarial perturbation to effectively protect privacy while maintaining high image quality.

Contribution

It introduces a novel system integrating attribute disentanglement, face swapping, and adversarial vector mapping for flexible face de-identification.

Findings

Effective removal of original identity via face swapping

Generation of high-quality de-identified images

Reduced identity recognition by models through adversarial perturbation

Abstract

With the identity information in face data more closely related to personal credit and property security, people pay increasing attention to the protection of face data privacy. In different tasks, people have various requirements for face de-identification (De-ID), so we propose a systematical solution compatible for these De-ID operations. Firstly, an attribute disentanglement and generative network is constructed to encode two parts of the face, which are the identity (facial features like mouth, nose and eyes) and expression (including expression, pose and illumination). Through face swapping, we can remove the original ID completely. Secondly, we add an adversarial vector mapping network to perturb the latent code of the face image, different from previous traditional adversarial methods. Through this, we can construct unrestricted adversarial image to decrease ID similarity recognized by model. Our method can flexibly de-identify the face data in various ways and the processed images have high image quality.