# iFADIT: Invertible Face Anonymization via Disentangled Identity Transform

arXiv: https://arxiv.org/abs/2501.04390 · HTML: https://mlsanity.com/paper/2501.04390/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 8 Jan 2025.

## Builds on (most cited first, 12 of 12)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation](https://mlsanity.com/paper/2008.00951/) (2020)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [Diff-Privacy: Diffusion-based Face Privacy Protection](https://mlsanity.com/paper/2309.05330/) (2023)
- [G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors](https://mlsanity.com/paper/2408.09458/) (2024)
- [Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming](https://mlsanity.com/paper/2101.01060/) (2021)
- [The UU-Net: Reversible Face De-Identification for Visual Surveillance Video Footage](https://mlsanity.com/paper/2007.04316/) (2020)
- [Editing Out-of-domain GAN Inversion via Differential Activations](https://mlsanity.com/paper/2207.08134/) (2022)
- [StyleID: Identity Disentanglement for Anonymizing Faces](https://mlsanity.com/paper/2212.13791/) (2022)
- [On Generating Identifiable Virtual Faces](https://mlsanity.com/paper/2110.07986/) (2021)
- [A Key-Driven Framework for Identity-Preserving Face Anonymization](https://mlsanity.com/paper/2409.03434/) (2024)

## Built on by (most cited first, 1 of 1)

- [Secure and reversible face anonymization with diffusion models](https://mlsanity.com/paper/2510.01031/) (2025)

## Abstract (arXiv)

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.