Clinically Grounded Privacy Evaluation of Medical LMs

• URL: http://arxiv.org/abs/2606.09590v1
• Date: Mon, 08 Jun 2026 15:02:19 GMT
• Title: Clinically Grounded Privacy Evaluation of Medical LMs
• Abstract summary: We introduce a clinically grounded framework that evaluates leakage along a graded axis of adversarial access.<n>Applying the framework to an LM pretrained on 378k clinical notes, we find that routine encounter metadata elicits high rates of verbatim memorization.
• Score: 14.192902006563045
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Medical language models (LMs) can memorize and reproduce protected health information, but privacy evaluations often focus on recovery of training text rather than disclosure under realistic threat models. We introduce a clinically grounded framework that evaluates leakage along a graded axis of adversarial access, ranging from publicly inferable demographics to leaked note fragments. At each tier, we measure verbatim memorization of patient-specific text and semantic leakage of sensitive diagnoses. Applying the framework to an LM pretrained on 378k clinical notes, we find that routine encounter metadata (i.e. name, date of birth, provider, practice, visit date) elicits high rates of verbatim memorization across a patient's timeline and sensitive-diagnosis recovery (AUROC 0.91 for abortion, 0.81 for HIV). At the same time, exact-match memorization can overstate disclosure: 36% of memorized tokens reflect templated documentation. Our work highlights the risks of training on longitudinal clinical data, providing a practical framework for contextual privacy evaluation of medical LMs.

Related papers

• Detecting Clinical Discrepancies in Health Coaching Agents: A Dual-Stream Memory and Reconciliation Architecture [71.46525715889656]
  General-purpose agent memory systems optimize for coherence by overwriting older facts with the user's latest statement.<n>We introduce a Dual-Stream Memory Architecture that strictly separates the patient narrative from the structured clinical record.<n>We evaluate this architecture on 26 patients across 675 longitudinal wellness coaching sessions.
  arXiv  Detail & Related papers  (2026-04-29T17:59:28Z)
• An Investigation of Memorization Risk in Healthcare Foundation Models [21.94560578418064]
  We introduce a suite of black-box evaluation tests to assess privacy-related risks in foundation models trained on structured EHR data.<n>Our framework includes methods for probing memorization at both the embedding and generative levels, and aims to distinguish between model generalization and harmful memorization in clinically relevant settings.
  arXiv  Detail & Related papers  (2025-10-14T19:55:07Z)
• Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications [42.69954853399731]
  Large Language Models (LLMs) have demonstrated significant potential in medicine.<n>We present the first comprehensive evaluation of memorization of LLMs in medicine.<n>The results demonstrate that memorization is prevalent across all adaptation scenarios and significantly higher than reported in the general domain.
  arXiv  Detail & Related papers  (2025-09-10T14:02:18Z)
• DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization [13.038800602897354]
  We develop an adversarial approach using a large language model to re-identify the patient corresponding to a redacted clinical note. Our method uses a large language model to reidentify the patient corresponding to a redacted clinical note. Although ClinicalBERT was the most effective, masking all identified PII, our tool still reidentified 9% of clinical notes.
  arXiv  Detail & Related papers  (2024-10-22T14:06:31Z)
• Retrieval-Augmented and Knowledge-Grounded Language Models for Faithful Clinical Medicine [68.7814360102644]
  We propose the Re$3$Writer method with retrieval-augmented generation and knowledge-grounded reasoning. We demonstrate the effectiveness of our method in generating patient discharge instructions.
  arXiv  Detail & Related papers  (2022-10-23T16:34:39Z)
• Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [56.72488923420374]
  Pre-trained language models (LMs) have shown great potential for cross-lingual transfer in low-resource settings. We show the few-shot cross-lingual transfer property of LMs for named recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan) clinical notes de-identification in the stroke.
  arXiv  Detail & Related papers  (2022-04-10T21:46:52Z)
• Classifying Cyber-Risky Clinical Notes by Employing Natural Language Processing [9.77063694539068]
  Recently, some states within the United States of America require patients to have open access to their clinical notes. This research investigates methods for identifying security/privacy risks within clinical notes.
  arXiv  Detail & Related papers  (2022-03-24T00:36:59Z)
• Towards more patient friendly clinical notes through language models and ontologies [57.51898902864543]
  We present a novel approach to automated medical text based on word simplification and language modelling. We use a new dataset pairs of publicly available medical sentences and a version of them simplified by clinicians. Our method based on a language model trained on medical forum data generates simpler sentences while preserving both grammar and the original meaning.
  arXiv  Detail & Related papers  (2021-12-23T16:11:19Z)
• Self-supervised Answer Retrieval on Clinical Notes [68.87777592015402]
  We introduce CAPR, a rule-based self-supervision objective for training Transformer language models for domain-specific passage matching. We apply our objective in four Transformer-based architectures: Contextual Document Vectors, Bi-, Poly- and Cross-encoders. We report that CAPR outperforms strong baselines in the retrieval of domain-specific passages and effectively generalizes across rule-based and human-labeled passages.
  arXiv  Detail & Related papers  (2021-08-02T10:42:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.