# Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesis

arXiv: https://arxiv.org/abs/2307.01148 · HTML: https://mlsanity.com/paper/2307.01148/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 15 of 15)

- [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)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [Diffusion Models for Implicit Image Segmentation Ensembles](https://mlsanity.com/paper/2112.03145/) (2021)
- [Unsupervised Medical Image Translation with Adversarial Diffusion Models](https://mlsanity.com/paper/2207.08208/) (2022)
- [Adaptive Diffusion Priors for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2207.05876/) (2022)
- [Generating large labeled data sets for laparoscopic image processing tasks using unpaired image-to-image translation](https://mlsanity.com/paper/1907.02882/) (2019)
- [Cross-Domain Conditional Generative Adversarial Networks for Stereoscopic Hyperrealism in Surgical Training](https://mlsanity.com/paper/1906.10011/) (2019)

## Built on by (most cited first, 19 of 19)

- [Generalization in diffusion models arises from geometry-adaptive harmonic representations](https://mlsanity.com/paper/2310.02557/) (2023)
- [On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity](https://mlsanity.com/paper/2506.03719/) (2025)
- [Generalization through variance: how noise shapes inductive biases in diffusion models](https://mlsanity.com/paper/2504.12532/) (2025)
- [On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook](https://mlsanity.com/paper/2307.16680/) (2023)
- [Replication in Visual Diffusion Models: A Survey and Outlook](https://mlsanity.com/paper/2408.00001/) (2024)
- [A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI](https://mlsanity.com/paper/2311.11383/) (2023)
- [Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Data](https://mlsanity.com/paper/2402.01054/) (2024)
- [Navigating the Latent Space Dynamics of Neural Models](https://mlsanity.com/paper/2505.22785/) (2025)
- [Synthetic Data in Radiological Imaging: Current State and Future Outlook](https://mlsanity.com/paper/2407.01561/) (2024)
- [CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographs](https://mlsanity.com/paper/2505.10496/) (2025)
- [Diffusion models under low-noise regime](https://mlsanity.com/paper/2506.07841/) (2025)
- [MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection](https://mlsanity.com/paper/2405.19458/) (2024)
- [LCMem: A Universal Model for Robust Image Memorization Detection](https://mlsanity.com/paper/2512.14421/) (2025)
- [The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation](https://mlsanity.com/paper/2502.07516/) (2025)
- [Latent Pollution Model: The Hidden Carbon Footprint in 3D Image Synthesis](https://mlsanity.com/paper/2407.14892/) (2024)
- [A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis](https://mlsanity.com/paper/2509.16582/) (2025)
- [On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models](https://mlsanity.com/paper/2508.16154/) (2025)
- [Trustworthy Large Models in Vision: A Survey](https://mlsanity.com/paper/2311.09680/) (2023)
- [Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++](https://mlsanity.com/paper/2609.03615/) (2026)

## Abstract (arXiv)

Generative latent diffusion models have been established as state-of-the-art in data generation. One promising application is generation of realistic synthetic medical imaging data for open data sharing without compromising patient privacy. Despite the promise, the capacity of such models to memorize sensitive patient training data and synthesize samples showing high resemblance to training data samples is relatively unexplored. Here, we assess the memorization capacity of 3D latent diffusion models on photon-counting coronary computed tomography angiography and knee magnetic resonance imaging datasets. To detect potential memorization of training samples, we utilize self-supervised models based on contrastive learning. Our results suggest that such latent diffusion models indeed memorize training data, and there is a dire need for devising strategies to mitigate memorization.