Keywords: Privacy, Machine Learning, Time-Series, Membership Inference
Verify Author List: I have double-checked the author list and understand that additions and removals will not be allowed after the submission deadline.
TL;DR: This paper examines the privacy risks of medical time-series prediction models by enhancing Membership Inference Attacks with new features based on seasonality and trend components, greatly improving the identification of member samples.
Abstract: Analyzing time-series data that may contain personal information, particularly in the medical field, presents serious privacy concerns. Sensitive health data from patients is often used to train machine-learning models for diagnostics and ongoing care. Assessing the privacy risk of such models is crucial to making knowledgeable decisions on whether to use a model in production, share it with third parties, or deploy it in patients’ homes. Membership Inference Attacks (MIA) are a key method for this kind of evaluation, however time-series prediction models have not been thoroughly studied in this context.
We explore existing MIA techniques on time-series models, and introduce new features, focusing on the seasonality and trend components of the data. Seasonality is estimated using a multivariate Fourier transform, and a low-degree polynomial is used to approximate trends. We applied these techniques to various types of time-series models, using datasets from the health domain. Our results demonstrate that these new features enhance the effectiveness of MIAs in identifying membership, improving the understanding of privacy risks in medical data applications.
A Signed Permission To Publish Form In Pdf: pdf
Primary Area: Trustworthy Machine Learning (accountability, explainability, transparency, causality, fairness, privacy, robustness, autoML, etc.)
Paper Checklist Guidelines: I certify that all co-authors of this work have read and commit to adhering to the guidelines in Call for Papers.
Student Author: Yes
Submission Number: 102
Loading