ArticleJournal of biomedical informatics2022
Membership inference attacks against synthetic health data.
Article in Journal of biomedical informatics, 2022. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 27 papers, 3 of them syntheses that pooled it.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
27 citing papers in PubMed, 3 syntheses or guidelines pooled it.
- Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit.Journal of the American Medical Informatics Association : JAMIA · 2026Pooled it
- [Empowering narrative medicine with artificial intelligence: a new perspective in pediatric medical education].Zhongguo dang dai er ke za zhi = Chinese journal of contemporary pediatrics · 2026Pooled it
- Safeguarding biomedical AI: a critical scoping review of privacy-enhancing technologies, hybrid approaches, and deployment models.Frontiers in digital health · 2026Pooled it
- Privacy and Security Throughout the Health Data Life Cycle: From Primary Care to Research Networks.Annual review of biomedical data science · 2026Review
- Reward-Guided Generation Improves the Scientific Utility of Synthetic Biomedical Data.medRxiv : the preprint server for health sciences · 2026Article
- Scalable and Privacy-Conscious End-to-End Processing of Large-Scale Clinical Data for Precision Medicine: Empirical Evaluation Study.JMIR medical informatics · 2026Article
- Deep generative hidden Markov models for synthetic patient data generation: a novel approach for medical AI research.BMC medical informatics and decision making · 2026Article
- Implementing generative artificial intelligence in precision oncology: safety, governance, and significance.Journal of hematology & oncology · 2026Review
- From model failure to system harm: operationalizing a sociotechnical pathway for healthcare AI safety.Frontiers in artificial intelligence · 2026Article
- Toward Audit-Ready Standards for Synthetic Cohorts in Health Decision Science.Health data science · 2026Article
- Biomedical data repositories require governance for artificial intelligence/machine learning applications at every step.JAMIA open · 2025Article
- A consensus privacy metrics framework for synthetic data.Patterns (New York, N.Y.) · 2025Article
- Article
- Addressing contemporary threats in anonymised healthcare data using privacy engineering.NPJ digital medicine · 2025Review
- Using UMAP for Partially Synthetic Healthcare Tabular Data Generation and Validation.Sensors (Basel, Switzerland) · 2024Article
- Beyond Multiple-Choice Accuracy: Real-World Challenges of Implementing Large Language Models in Healthcare.ArXiv · 2024Article
- Building an Ethical and Trustworthy Biomedical AI Ecosystem for the Translational and Clinical Integration of Foundation Models.Bioengineering (Basel, Switzerland) · 2024Review
- Privacy-Enhancing Technologies in Biomedical Data Science.Annual review of biomedical data science · 2024Review
- Generating Synthetic Electronic Health Record Data Using Generative Adversarial Networks: Tutorial.JMIR AI · 2024Article
- Toward Identifying New Risk Aversions and Subsequent Limitations and Biases When Making De-identified Structured Data Sets Openly Available in a Post-LLM world.AMIA ... Annual Symposium proceedings. AMIA Symposium · 2024Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
Abstract
Synthetic data generation has emerged as a promising method to protect patient privacy while sharing individual-level health data. Intuitively, sharing synthetic data should reduce disclosure risks because no explicit linkage is retained between the synthetic records and the real data upon which it is based. However, the risks associated with synthetic data are still evolving, and what seems protected today may not be tomorrow. In this paper, we show that membership inference attacks, whereby an adversary infers if the data from certain target individuals (known to the adversary a priori) were relied upon by the synthetic data generation process, can be substantially enhanced through state-of-the-art machine learning frameworks, which calls into question the protective nature of existing synthetic data generators. Specifically, we formulate the membership inference problem from the perspective of the data holder, who aims to perform a disclosure risk assessment prior to sharing any health data. To support such an assessment, we introduce a framework for effective membership inference against synthetic health data without specific assumptions about the generative model or a well-defined data structure, leveraging the principles of contrastive representation learning. To illustrate the potential for such an attack, we conducted experiments against synthesis approaches using two datasets derived from several health data resources (Vanderbilt University Medical Center, the All of Us Research Program) to determine the upper bound of risk brought by an adversary who invokes an optimal strategy. The results indicate that partially synthetic data are vulnerable to membership inference at a very high rate. By contrast, fully synthetic data are only marginally susceptible and, in most cases, could be deemed sufficiently protected from membership inference.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.