# Refacing: reconstructing anonymized facial features using GANs

arXiv: https://arxiv.org/abs/1810.06455 · HTML: https://mlsanity.com/paper/1810.06455/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2018.

## Built on by (most cited first, 9 of 9)

- [Neuralizer: General Neuroimage Analysis without Re-Training](https://mlsanity.com/paper/2305.02644/) (2023)
- [Challenges for machine learning in clinical translation of big data imaging studies](https://mlsanity.com/paper/2107.05630/) (2021)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [A Privacy-Preserving Walk in the Latent Space of Generative Models for Medical Applications](https://mlsanity.com/paper/2307.02984/) (2023)
- [k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment](https://mlsanity.com/paper/2303.10824/) (2023)
- [Fast refacing of MR images with a generative neural network lowers re-identification risk and preserves volumetric consistency](https://mlsanity.com/paper/2305.16922/) (2023)
- [Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential](https://mlsanity.com/paper/2501.18834/) (2025)
- [Interpretability of Uncertainty: Exploring Cortical Lesion Segmentation in Multiple Sclerosis](https://mlsanity.com/paper/2407.05761/) (2024)
- [Quantifying privacy risks in foundation model representations of brain MRI](https://mlsanity.com/paper/2610.20494/) (2026)

## Abstract (arXiv)

Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN unsupervised image-to-image translation framework on sagittal slices of T1 MR images, in order to reconstruct facial features from anonymized data. We applied the CycleGAN framework on both face-blurred and face-removed images. Our results show that face blurring may not provide adequate protection against malicious attempts at identifying the subjects, while face removal provides more robust anonymization, but is still partially reversible.