# Protecting patient privacy in clinical foundation models: Technical and legal perspectives

arXiv: https://arxiv.org/abs/2608.07705 · HTML: https://mlsanity.com/paper/2608.07705/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 78 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 30 of 33)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [MedGemma Technical Report](https://mlsanity.com/paper/2507.05201/) (2025)
- [MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data](https://mlsanity.com/paper/2304.08247/) (2023)
- [GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records](https://mlsanity.com/paper/2203.03540/) (2022)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [Safety Layers in Aligned Large Language Models: The Key to LLM Security](https://mlsanity.com/paper/2408.17003/) (2024)
- [On Memorization in Diffusion Models](https://mlsanity.com/paper/2310.02664/) (2023)
- [Synthetic Data -- Anonymisation Groundhog Day](https://mlsanity.com/paper/2011.07018/) (2020)
- [Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions](https://mlsanity.com/paper/2404.03264/) (2024)
- [Zero Shot Health Trajectory Prediction Using Transformer](https://mlsanity.com/paper/2407.21124/) (2024)
- [International AI Safety Report](https://mlsanity.com/paper/2501.17805/) (2025)
- [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)
- [Disparate Vulnerability to Membership Inference Attacks](https://mlsanity.com/paper/1906.00389/) (2019)
- [Source Inference Attacks in Federated Learning](https://mlsanity.com/paper/2109.05659/) (2021)
- [A Multi-Center Study on the Adaptability of a Shared Foundation Model for Electronic Health Records](https://mlsanity.com/paper/2311.11483/) (2023)
- [Privacy Auditing of Large Language Models](https://mlsanity.com/paper/2503.06808/) (2025)
- [Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecurity](https://mlsanity.com/paper/2401.07348/) (2024)
- [Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions](https://mlsanity.com/paper/2412.02621/) (2024)
- [The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text](https://mlsanity.com/paper/2502.14921/) (2025)
- [LLM Unlearning with LLM Beliefs](https://mlsanity.com/paper/2510.19422/) (2025)
- [Hubble: a Model Suite to Advance the Study of LLM Memorization](https://mlsanity.com/paper/2510.19811/) (2025)
- [De-identification is not enough: a comparison between de-identified and synthetic clinical notes](https://mlsanity.com/paper/2402.00179/) (2024)
- [Pretraining with hierarchical memories: separating long-tail and common knowledge](https://mlsanity.com/paper/2510.02375/) (2025)
- [Large-scale online deanonymization with LLMs](https://mlsanity.com/paper/2602.16800/) (2026)
- [Building Safe GenAI Applications: An End-to-End Overview of Red Teaming for Large Language Models](https://mlsanity.com/paper/2503.01742/) (2025)
- [The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behavior](https://mlsanity.com/paper/2509.19364/) (2025)

## Built on by (most cited first, 1 of 1)

- [Quantifying privacy risks in foundation model representations of brain MRI](https://mlsanity.com/paper/2610.20494/) (2026)

## Abstract (arXiv)

Clinical foundation models trained on large-scale patient data are increasingly used for decision support, screening, and public health planning. As deployment expands, privacy risk arises from model-mediated leakage, yet its prevalence and severity remain poorly quantified. Models can disclose sensitive training artifacts, enabling patient re-identification in ways not captured by data-handling controls alone. As a result, existing frameworks, including HIPAA and GDPR, offer limited protection against assessing and addressing. We propose a practical framework for assessing privacy risk in clinical foundation models, illustrate realistic leakage scenarios across deployment settings, map them to legal regimes, and outline complementary technical and legal mitigations. Our analysis provides a context-aware risk assessment grounded in realistic usage to preserve the value of medical foundation models while rigorously safeguarding patient privacy.