# Enabling PSO-Secure Synthetic Data Sharing Using Diversity-Aware Diffusion Models

arXiv: https://arxiv.org/abs/2506.17975 · HTML: https://mlsanity.com/paper/2506.17975/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 22 Jun 2025.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 30 of 30)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Data](https://mlsanity.com/paper/2103.08562/) (2021)
- [MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation](https://mlsanity.com/paper/2304.04106/) (2023)
- [Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis](https://mlsanity.com/paper/2303.12644/) (2023)
- [Towards Formalizing the GDPR's Notion of Singling Out](https://mlsanity.com/paper/1904.06009/) (2019)
- [Image Generation Diversity Issues and How to Tame Them](https://mlsanity.com/paper/2411.16171/) (2024)
- [Synthetic Augmentation with Large-scale Unconditional Pre-training](https://mlsanity.com/paper/2308.04020/) (2023)
- [EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing](https://mlsanity.com/paper/2406.00808/) (2024)
- [Synthesising Rare Cataract Surgery Samples with Guided Diffusion Models](https://mlsanity.com/paper/2308.02587/) (2023)
- [Controllable and Efficient Multi-Class Pathology Nuclei Data Augmentation using Text-Conditioned Diffusion Models](https://mlsanity.com/paper/2407.14426/) (2024)
- [Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models](https://mlsanity.com/paper/2212.14306/) (2022)
- [Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models](https://mlsanity.com/paper/2405.16516/) (2024)
- [RadiomicsFill-Mammo: Synthetic Mammogram Mass Manipulation with Radiomics Features](https://mlsanity.com/paper/2407.05683/) (2024)
- [CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image Classification](https://mlsanity.com/paper/2307.06182/) (2023)
- [Generating Progressive Images from Pathological Transitions via Diffusion Model](https://mlsanity.com/paper/2311.12316/) (2023)
- [An Organism Starts with a Single Pix-Cell: A Neural Cellular Diffusion for High-Resolution Image Synthesis](https://mlsanity.com/paper/2407.03018/) (2024)
- [Cross-modulated Few-shot Image Generation for Colorectal Tissue Classification](https://mlsanity.com/paper/2304.01992/) (2023)
- [Auto-Generating Weak Labels for Real & Synthetic Data to Improve Label-Scarce Medical Image Segmentation](https://mlsanity.com/paper/2404.17033/) (2024)
- [Hyperparameter-Free Medical Image Synthesis for Sharing Data and Improving Site-Specific Segmentation](https://mlsanity.com/paper/2404.06240/) (2024)
- [Uncovering Hidden Subspaces in Video Diffusion Models Using Re-Identification](https://mlsanity.com/paper/2411.04956/) (2024)

## Built on by (most cited first, 3 of 3)

- [LCMem: A Universal Model for Robust Image Memorization Detection](https://mlsanity.com/paper/2512.14421/) (2025)
- [Flow Matching with Optimized Subclass Priors for Medical Image Augmentation](https://mlsanity.com/paper/2605.16469/) (2026)
- [A Data-Interventional Framework for Auditing Privacy and Fairness in Generative Medical Imaging](https://mlsanity.com/paper/2609.26623/) (2026)

## Abstract (arXiv)

Synthetic data has recently reached a level of visual fidelity that makes it nearly indistinguishable from real data, offering great promise for privacy-preserving data sharing in medical imaging. However, fully synthetic datasets still suffer from significant limitations: First and foremost, the legal aspect of sharing synthetic data is often neglected and data regulations, such as the GDPR, are largley ignored. Secondly, synthetic models fall short of matching the performance of real data, even for in-domain downstream applications. Recent methods for image generation have focused on maximising image diversity instead of fidelity solely to improve the mode coverage and therefore the downstream performance of synthetic data. In this work, we shift perspective and highlight how maximizing diversity can also be interpreted as protecting natural persons from being singled out, which leads to predicate singling-out (PSO) secure synthetic datasets. Specifically, we propose a generalisable framework for training diffusion models on personal data which leads to unpersonal synthetic datasets achieving performance within one percentage point of real-data models while significantly outperforming state-of-the-art methods that do not ensure privacy. Our code is available at https://github.com/MischaD/Trichotomy.