5 papers
Subgroup Membership Inference Audits of Differentially Private Synthetic Text
Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +2
Synthetic data releases are increasingly proposed in the literature as a means of sharing realistic data replicas in lieu of sensitive private datasets. Even when the worst-case pr…
TermGPT: Multi-Level Contrastive Fine-Tuning for Terminology Adaptation in Legal and Financial Domain
Yidan Sun, Mengying Zhu, Feiyue Chen +5
Large language models (LLMs) have demonstrated impressive performance in text generation tasks; however, their embedding spaces often suffer from the isotropy problem, resulting in…
SynBench: A Benchmark for Differentially Private Text Generation
Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +9
Synthetic text generation with Differential Privacy (DP) guarantees emerges as a principled approach that can enable the sharing of sensitive datasets across institutional and regu…
Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies
Yuping Wu, Viktor Schlegel, Warren Del-Pinto +11
In high-stakes domains such as healthcare, privacy concerns severely limit the use of real-world training data. Differentially private (DP) synthetic data offers a promising altern…
Evaluating Differentially Private Generation of Domain-Specific Text
Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +7
Generative AI offers transformative potential for high-stakes domains such as healthcare and finance, yet privacy and regulatory barriers hinder the use of real-world data. To addr…