# A Key-Driven Framework for Identity-Preserving Face Anonymization

arXiv: https://arxiv.org/abs/2409.03434 · HTML: https://mlsanity.com/paper/2409.03434/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 20 of 20)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [DeepPrivacy: A Generative Adversarial Network for Face Anonymization](https://mlsanity.com/paper/1909.04538/) (2019)
- [CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks](https://mlsanity.com/paper/2005.09544/) (2020)
- [AnonymousNet: Natural Face De-Identification with Measurable Privacy](https://mlsanity.com/paper/1904.12620/) (2019)
- [Attribute-preserving Face Dataset Anonymization via Latent Code Optimization](https://mlsanity.com/paper/2303.11296/) (2023)
- [Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain](https://mlsanity.com/paper/2207.07316/) (2022)
- [Password-conditioned Anonymization and Deanonymization with Face Identity Transformers](https://mlsanity.com/paper/1911.11759/) (2019)
- [IdentityDP: Differential Private Identification Protection for Face Images](https://mlsanity.com/paper/2103.01745/) (2021)
- [DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain](https://mlsanity.com/paper/2207.07340/) (2022)
- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [Fawkes: Protecting Privacy against Unauthorized Deep Learning Models](https://mlsanity.com/paper/2002.08327/) (2020)
- [Anonymizing k-Facial Attributes via Adversarial Perturbations](https://mlsanity.com/paper/1805.09380/) (2018)
- [On Generating Identifiable Virtual Faces](https://mlsanity.com/paper/2110.07986/) (2021)
- [Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection](https://mlsanity.com/paper/2307.00481/) (2023)

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

- [iFADIT: Invertible Face Anonymization via Disentangled Identity Transform](https://mlsanity.com/paper/2501.04390/) (2025)

## Abstract (arXiv)

Virtual faces are crucial content in the metaverse. Recently, attempts have been made to generate virtual faces for privacy protection. Nevertheless, these virtual faces either permanently remove the identifiable information or map the original identity into a virtual one, which loses the original identity forever. In this study, we first attempt to address the conflict between privacy and identifiability in virtual faces, where a key-driven face anonymization and authentication recognition (KFAAR) framework is proposed. Concretely, the KFAAR framework consists of a head posture-preserving virtual face generation (HPVFG) module and a key-controllable virtual face authentication (KVFA) module. The HPVFG module uses a user key to project the latent vector of the original face into a virtual one. Then it maps the virtual vectors to obtain an extended encoding, based on which the virtual face is generated. By simultaneously adding a head posture and facial expression correction module, the virtual face has the same head posture and facial expression as the original face. During the authentication, we propose a KVFA module to directly recognize the virtual faces using the correct user key, which can obtain the original identity without exposing the original face image. We also propose a multi-task learning objective to train HPVFG and KVFA. Extensive experiments demonstrate the advantages of the proposed HPVFG and KVFA modules, which effectively achieve both facial anonymity and identifiability.