Article

Membership Disclosure Evaluation for Synthetic Clinical Text Generated by LLM via Dynamic Few-Shot In-Context Learning

2026-03-30

Abstract excerpt

<title>Abstract</title> <p> <bold>Purpose</bold> : LLMs are increasingly used to generate synthetic clinical notes for data sharing, but membership inference attacks (MIAs) can reveal whether specific real notes appeared in prompts or training data. Prior studies often examine static few-shot prompts, i.e., fixed exemplar notes that remain the same across queries. We investigate MIAs on synthetic clinical text...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 79064101-8fb2-5ae7-8832-ac412812cb64
DOI: 10.21203/rs.3.rs-8997592/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Membership Disclosure Evaluation for Synthetic Clinical Text Generated by LLM via Dynamic Few-Shot In-Context LearningDOI 10.21203/rs.3.rs-8997592/v1Read

FedMedSecure: Federated Few-Shot Learning with Cross-Attention Mechanisms and Explainable AI for Collaborative Healthcare CybersecuritySemantic proximity Read

Data Quality Verification Metrics in Medicine: Experiments and Evaluations from the Perspectives of Safety and UtilitySemantic proximity Read

Utility is all you need: fidelity-agnostic synthetic data generationSemantic proximity Read

Hide and Seek: Privacy-Preserving Artificial Intelligence with a Feasibility Study in Rare Disease DiagnosisSemantic proximity Read

Generating synthetic electronic health record data: a methodological scoping review with benchmarking on phenotype data and open-source software.Semantic proximity Read

Synthetic data for privacy-preserving clinical risk predictionSemantic proximity Read

On the Fidelity versus Privacy and Utility Trade-Off of Synthetic Patient DataSemantic proximity Read

SynthGuard-ReleaseBench: Locked-Audit Evidence for Synthetic Tabular Data ReleasesSemantic proximity Read

Evaluating Fidelity and Machine Learning Utility of Synthetic Tabular Data Generated Using Generative ModelsSemantic proximity Read

SynTrustBench: An Evidence-Gated and Executable Benchmark for Trustworthiness Claims in Synthetic Clinical DataSemantic proximity Read

<em>ppAIsec</em>: Privacy-Preserving Artificial Intelligence Models in Healthcare Security—A Synthesis of AI FrameworksSemantic proximity Read

Actionability of Synthetic Data in a Heterogeneous and Rare Healthcare Demographic; Adolescents and Young Adults (AYAs) with CancerSemantic proximity Read