iFADIT: Invertible Face Anonymization via Disentangled Identity Transform

TL;DR

iFADIT introduces an invertible face anonymization framework that disentangles identity features and securely transforms them, enabling high-quality anonymized faces and reversible de-anonymization with a secret key, enhancing privacy and utility.

Contribution

The paper presents a novel invertible face anonymization method using disentangled identity attributes and flow-based models, allowing reversible anonymization and high-quality image synthesis.

Findings

Outperforms existing methods in anonymity and image quality.

Enables reversible face de-anonymization with a secret key.

Demonstrates robustness against reconstruction attacks.

Abstract

Face anonymization aims to conceal the visual identity of a face to safeguard the individual's privacy. Traditional methods like blurring and pixelation can largely remove identifying features, but these techniques significantly degrade image quality and are vulnerable to deep reconstruction attacks. Generative models have emerged as a promising solution for anonymizing faces while preserving a natural appearance. However, many still face limitations in visual quality and often overlook the potential to recover the original face from the anonymized version, which can be valuable in specific contexts such as image forensics. This paper proposes a novel framework named iFADIT, an acronym for Invertible Face Anonymization via Disentangled Identity Transform. The framework features a disentanglement architecture coupled with a secure flow-based model: the former decouples identity information from non-identifying attributes, while the latter transforms the decoupled identity into an anonymized version in an invertible manner controlled by a secret key. The anonymized face can then be reconstructed based on a pre-trained StyleGAN that ensures high image quality and realistic facial details. Recovery of the original face (aka de-anonymization) is possible upon the availability of the matching secret, by inverting the anonymization process based on the same set of model parameters. Furthermore, a dedicated secret-key mechanism along with a dual-phase training strategy is devised to ensure the desired properties of face anonymization. Qualitative and quantitative experiments demonstrate the superiority of the proposed approach in anonymity, reversibility, security, diversity, and interpretability over competing methods.