← Back to all news
arXiv Computation and Language By Sasha Ronaghi, Sana Tonekaboni, Lena Stempfle, Vivian Utti, Jordan Li Cahoon, Nathaniel Hendrix, Ayin Vala, Marzyeh Ghassemi, Emily Alsentzer

Clinically Grounded Privacy Evaluation of Medical LMs

Read the original on arXiv Computation and Language →

The paper introduces a clinically grounded privacy evaluation framework for medical language models, assessing leakage across a spectrum of adversarial access levels—from publicly inferable demographics to leaked note fragments. Using this framework on an LM pretrained on 378,000 clinical notes, the authors find that routine encounter metadata leads to high verbatim memorization and significant recovery of sensitive diagnoses (e.g., AUROC 0.91 for abortion, 0.82 for HIV). They also note that exact-match memorization can overstate disclosure, with 36% of memorized tokens being templated documentation, underscoring the risks of training on longitudinal clinical data and offering a reusable evaluation tool.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
2d ago

Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies

The paper introduces Term2Note, a method for generating full-length clinical notes under differential privacy constraints. It separates content and form, conditioning note sections on medical terms and applying distinct DP protections to terms and notes, followed by a DP quality maximizer. Experiments show that the synthetic notes closely match real clinical notes in statistical properties, and models trained on them perform comparably to those trained on real data, outperforming existing DP text generation baselines.

By Yuping Wu, Viktor Schlegel, Warren Del-Pinto, Srinivasan Nandakumar, Iqra Zahid, Yidan Sun, Hai Li, Usama Farghaly Omar, Amirah Jasmine, Arun-Kumar Kaliya-Perumal, Chun Shen Tham, Gabriel Connors, Anil A Bharath, Goran Nenadic
safety
More like this →
arXiv Machine Learning
Aug 19

Quantifying Memorization and Privacy Risks in Genomic Language Models

The paper introduces a comprehensive privacy evaluation framework for genomic language models (GLMs) that quantifies memorization risks using perplexity-based detection, canary sequence extraction, and membership inference. By planting canary sequences at different repetition rates in synthetic and real datasets, the authors systematically assess how repetition, model capacity, and training dynamics affect memorization across various GLM architectures. The study demonstrates that GLMs do memorize training data to varying degrees and that no single attack method fully captures this risk, highlighting the necessity of multi-vector privacy auditing for genomic AI systems.

By Alexander Nemecek, Wenbiao Li, Xiaoqian Jiang, Jaideep Vaidya, Erman Ayday
llmsfine-tuningsafety
More like this →
arXiv Machine Learning
Aug 27

Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models

The paper examines how supervised fine-tuning (SFT) of large language models can leak personally identifiable information (PII) when the fine-tuning data contains user-provided sensitive details. It introduces COVA, a coverage-aware decoding algorithm that improves targeted PII reconstruction from SFT models, especially when an adversary has limited contextual knowledge about a target. Experiments on medical and legal Q&A datasets show that even small proprietary SFT datasets can lead to significant privacy leakage via PII reconstruction.

By Sae Furukawa, Alina Oprea
llmsfine-tuningsafety
More like this →