Membership Inference Attacks Against Time-Series Models

Noam Koren, Abigail Goldsteen, Guy Amit, Ariel Farkash
Proceedings of the 16th Asian Conference on Machine Learning, PMLR 260:319-334, 2025.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v260-koren25a, title = {Membership Inference Attacks Against Time-Series Models}, author = {Koren, Noam and Goldsteen, Abigail and Amit, Guy and Farkash, Ariel}, booktitle = {Proceedings of the 16th Asian Conference on Machine Learning}, pages = {319--334}, year = {2025}, editor = {Nguyen, Vu and Lin, Hsuan-Tien}, volume = {260}, series = {Proceedings of Machine Learning Research}, month = {05--08 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v260/main/assets/koren25a/koren25a.pdf}, url = {https://proceedings.mlr.press/v260/koren25a.html}, 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.} }
Endnote
%0 Conference Paper %T Membership Inference Attacks Against Time-Series Models %A Noam Koren %A Abigail Goldsteen %A Guy Amit %A Ariel Farkash %B Proceedings of the 16th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Vu Nguyen %E Hsuan-Tien Lin %F pmlr-v260-koren25a %I PMLR %P 319--334 %U https://proceedings.mlr.press/v260/koren25a.html %V 260 %X 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.
APA
Koren, N., Goldsteen, A., Amit, G. & Farkash, A.. (2025). Membership Inference Attacks Against Time-Series Models. Proceedings of the 16th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 260:319-334 Available from https://proceedings.mlr.press/v260/koren25a.html.

Related Material