发表机构
Massachusetts Institute of Technology (MIT); The Broad Institute of MIT and Harvard; Borealis AI; Stanford University; Aalto University; Max Planck Institute for Tax Law and Public Finance; Stanford Law School; Harvard Law School; Petrie-Flom Center for Health Law Policy, Biotechnology & Bioethics（麻省理工学院（MIT）; 麻省理工学院与哈佛大学博德研究所; Borealis AI; 斯坦福大学; 阿尔托大学; 马克斯·普朗克税法与公共财政研究所; 斯坦福法学院; 哈佛法学院; 皮里-弗洛姆健康法律政策、生物技术与生物伦理中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对临床基础模型的隐私风险，提出实用评估框架，结合技术与法律措施缓解泄露，在保留模型价值的同时保护患者隐私。
AI 中文摘要
基于大规模患者数据训练的临床基础模型正越来越多地用于决策支持、筛查和公共卫生领域。随着其部署范围扩大，模型介导的信息泄露带来的隐私风险日益凸显，但该风险的普遍性与严重程度仍未得到充分量化。模型可能会泄露敏感的训练产物，从而以数据处理控制措施无法覆盖的方式实现患者重识别。现有框架包括HIPAA与GDPR，对这类间接威胁的指导有限。我们提出了一种用于评估临床基础模型隐私风险的实用框架，阐释了不同部署场景下的真实泄露情景，将其对应至法律制度，并概述了互补的技术与法律缓解措施。我们的分析基于真实使用场景提供了情境感知的风险评估，以在保留医学基础模型价值的同时严格保护患者隐私。
英文摘要
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.
Comments11 pages, 2 Figures, 1 Tables
