arXiv Machine Learning
Memorisation bias in medical AI
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computation and Language
Aug 25
Clinically Grounded Privacy Evaluation of Medical LMs
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.
arXiv AI
Aug 6
Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications
arXiv:2509. 08604v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated significant potential in medicine, with many studies adapting them through continued pre-training or fine-tuning on medical data to enhance domain-specific accuracy and safety.
arXiv Machine Learning
Jul 15
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
arXiv:2607. 12354v1 Announce Type: new Abstract: In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks.
arXiv Machine Learning
Jun 9
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
arXiv:2606. 08372v1 Announce Type: cross Abstract: Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute values from a synthetic release and a handful of known quasi-identifiers) has been studied only in scattered, hard-to-compare settings.
arXiv Machine Learning
Aug 28
Private and interpretable clinical prediction with quantum-inspired tensor train models
The paper demonstrates that publicly available clinical machine learning models, such as logistic regression (LR), pose significant privacy risks because attackers can recover model parameters and identify training cohorts through various membership inference attacks. The authors show that even small cohorts can be reliably identified and that common practices like cross-validation can worsen the risk. To mitigate this, they propose a quantum-inspired defense that tensorizes discretized models into tensor trains (TTs), which obfuscates parameters, preserves accuracy, and maintains interpretability while providing black‑box protection comparable to Differential Privacy.
arXiv Computation and Language
Sep 1
CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
The paper introduces MIMIC-DOS, a dataset derived from MIMIC-IV that focuses on ICU cases where patient symptoms and medical signs are discordant. It presents CARE, a privacy‑compliant multi‑stage agentic reasoning framework that uses a proprietary LLM to generate structured categories and transitions, while a local LLM performs evidence acquisition and decision‑making. In retrospective evaluations on MIMIC‑DOS, CARE outperforms other LLMs and agentic workflows, demonstrating stronger handling of conflicting clinical evidence while preserving patient privacy.