mlsanityData to 14 Oct 2026

Privacy Distillation: Reducing Re-identification Risk of Multimodal Diffusion Models

arXiv 2306.01322 ↗First posted 2 Jun 2023cs.LG cs.CR cs.CVcited by 18

On the map: Diffusion models → Robustness, privacy and adversarial aspects

also in 1 more
Abstract (arXiv)

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model without exposing it to identifiable data. Here, we are interested in the privacy issue faced by a data provider who wishes to share their data via a multimodal generative model. A question that immediately arises is ``How can a data provider ensure that the generative model is not leaking identifiable information about a patient?''. Our solution consists of (1) training a first diffusion model on real data (2) generating a synthetic dataset using this model and filtering it to exclude images with a re-identifiability risk (3) training a second diffusion model on the filtered synthetic data only. We showcase that datasets sampled from models trained with privacy distillation can effectively reduce re-identification risk whilst maintaining downstream performance.

Key facts. Cited by 18 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 40 of its 50 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

40 of 50 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Extracting Training Data from Diffusion Models30 Jan
  2. 2023Membership Inference of Diffusion Models24 Jan
  3. 2022Differentially Private Diffusion Models18 Oct

Other references · 37

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  11. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  12. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
25 more
  1. 2016Deep Learning with Differential Privacycited by 2,728
  2. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  3. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  4. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 700
  5. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 424
  6. 2022Making the Most of Text Semantics to Improve Biomedical Vision--Language Processingcited by 339
  7. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  8. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 327
  9. 2022Brain Imaging Generation with Latent Diffusion Modelscited by 268
  10. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 213
  11. 2021How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Modelscited by 196
  12. 2021TorchXRayVision: A library of chest X-ray datasets and modelscited by 131
  13. 2022Fast Unsupervised Brain Anomaly Detection and Segmentation with Diffusion Modelscited by 97
  14. 2022RoentGen: Vision-Language Foundation Model for Chest X-ray Generationcited by 89
  15. 2020Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classificationcited by 86
  16. 2020Improved Techniques for Training Single-Image GANscited by 78
  17. 2022What is Healthy? Generative Counterfactual Diffusion for Lesion Localizationcited by 52
  18. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  19. 2021Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Datacited by 38
  20. 2022Can segmentation models be trained with fully synthetically generated data?cited by 37
  21. 2022Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Imagescited by 35
  22. 2023Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?cited by 21
  23. 2020Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methodscited by 13
  24. 2022Indication as Prior Knowledge for Multimodal Disease Classification in Chest Radiographs with Transformerscited by 8
  25. 2022Why patient data cannot be easily forgotten?cited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 6; 2024: 5; 2025: 5; 2026: 2.

18 papers.

Sort:

By area:

  1. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  2. 2023White-box Membership Inference Attacks against Diffusion Modelscited by 42
  3. 2023Black-box Membership Inference Attacks against Fine-tuned Diffusion Modelscited by 35
  4. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  5. 2023RadEdit: stress-testing biomedical vision models via diffusion image editingcited by 28
  6. 2024From Pixel to Cancer: Cellular Automata in Computed Tomographycited by 20
  7. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  8. 2024Replication in Visual Diffusion Models: A Survey and Outlookcited by 11
  9. 2024Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Datacited by 9
  10. 2025One-Step Offline Distillation of Diffusion-based Models via Koopman Modelingcited by 9
  11. 2025CheXGenBench: A Unified Benchmark For Fidelity, Privacy and Utility of Synthetic Chest Radiographscited by 5
  12. 2024MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selectioncited by 4
6 more
  1. 2025The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generationcited by 3
  2. 2023SoK: Memorisation in machine learningcited by 1
  3. 2025SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generationcited by 1
  4. 2025RELICT: A Replica Detection Framework for Medical Image Generationcited by 0
  5. 2026MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoningcited by 0
  6. 2026Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attackscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Differentially Private Diffusion Models Generate Useful Synthetic Images
  2. 2024Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
  3. 2024Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
  4. 2025Does Training with Synthetic Data Truly Protect Privacy?
  5. 2024Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training
  6. 2024Model Will Tell: Training Membership Inference for Diffusion Models
  7. 2025Your Image Generator Is Your New Private Dataset
  8. 2024Differentially Private Fine-Tuning of Diffusion Models