# PrivacyGAN: robust generative image privacy

arXiv: https://arxiv.org/abs/2310.12590 · HTML: https://mlsanity.com/paper/2310.12590/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 19 Oct 2023.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [DeepPrivacy: A Generative Adversarial Network for Face Anonymization](https://mlsanity.com/paper/1909.04538/) (2019)
- [LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition](https://mlsanity.com/paper/2101.07922/) (2021)
- [Towards Measuring Fairness in AI: the Casual Conversations Dataset](https://mlsanity.com/paper/2104.02821/) (2021)
- [Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer](https://mlsanity.com/paper/2203.03121/) (2022)
- [Variational Model Inversion Attacks](https://mlsanity.com/paper/2201.10787/) (2022)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [FaceX-Zoo: A PyTorch Toolbox for Face Recognition](https://mlsanity.com/paper/2101.04407/) (2021)
- [Live Face De-Identification in Video](https://mlsanity.com/paper/1911.08348/) (2019)
- [Data Poisoning Won't Save You From Facial Recognition](https://mlsanity.com/paper/2106.14851/) (2021)
- [Attribute-preserving Face Dataset Anonymization via Latent Code Optimization](https://mlsanity.com/paper/2303.11296/) (2023)
- [Fast Geometrically-Perturbed Adversarial Faces](https://mlsanity.com/paper/1809.08999/) (2018)
- [SoK: Anti-Facial Recognition Technology](https://mlsanity.com/paper/2112.04558/) (2021)
- [GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions](https://mlsanity.com/paper/2305.02143/) (2023)

## Abstract (arXiv)

Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression.In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications. Drawing inspiration from Fawkes, our method entails shifting the original image within the embedding space towards a decoy image.We evaluate our approach using privacy metrics on traditional and novel facial image datasets. Additionally, we propose new criteria for evaluating the robustness of privacy-protection methods against unknown image recognition techniques, and we demonstrate that our approach is effective even in unknown embedding transfer scenarios. We also provide a human evaluation that further proves that the modified image preserves its utility as it remains recognisable as an image of the same person by friends and family.