# Local Differential Privacy Image Generation Using Flow-based Deep Generative Models

arXiv: https://arxiv.org/abs/2212.10688 · HTML: https://mlsanity.com/paper/2212.10688/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 20 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 8 of 8)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [DP-Image: Differential Privacy for Image Data in Feature Space](https://mlsanity.com/paper/2103.07073/) (2021)
- [Differentially Private Imaging via Latent Space Manipulation](https://mlsanity.com/paper/2103.05472/) (2021)
- [Obfuscation of Images via Differential Privacy: From Facial Images to General Images](https://mlsanity.com/paper/2102.11072/) (2021)

## Built on by (most cited first, 5 of 5)

- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges](https://mlsanity.com/paper/2407.00116/) (2024)
- [On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Models](https://mlsanity.com/paper/2407.16405/) (2024)
- [Exactly Minimax-Optimal Locally Differentially Private Sampling](https://mlsanity.com/paper/2410.22699/) (2024)
- [Locally Optimal Private Sampling: Beyond the Global Minimax](https://mlsanity.com/paper/2510.09485/) (2025)

## Abstract (arXiv)

Diagnostic radiologists need artificial intelligence (AI) for medical imaging, but access to medical images required for training in AI has become increasingly restrictive. To release and use medical images, we need an algorithm that can simultaneously protect privacy and preserve pathologies in medical images. To develop such an algorithm, here, we propose DP-GLOW, a hybrid of a local differential privacy (LDP) algorithm and one of the flow-based deep generative models (GLOW). By applying a GLOW model, we disentangle the pixelwise correlation of images, which makes it difficult to protect privacy with straightforward LDP algorithms for images. Specifically, we map images onto the latent vector of the GLOW model, each element of which follows an independent normal distribution, and we apply the Laplace mechanism to the latent vector. Moreover, we applied DP-GLOW to chest X-ray images to generate LDP images while preserving pathologies.