cs.CRNov 4, 2026

Timing is Everything: Inferring Temporal Membership in Continually Updated Models

Authors: Jie Fu, Xiangpeng Deng, Yuan Hong, Wendy Hui Wang

Organizations: Stevens Institute of Technology Hoboken, New Jersey, USA · University of Connecticut Storrs, Connecticut, USA

Abstract

Continual model updating has become a common practice in the deployment of machine learning systems. However, the dynamic training behaviors give rise to new risks not sufficiently addressed by existing studies. In this paper, we present the first systematic study of temporal privacy risk in continually updated deep learning models. We formalize the notion of temporal membership in continually updated models. We then define the temporal membership inference attack, which seeks to infer whether and when individual samples were involved in model training, at both timestamp-level and interval-level granularities. To this end, we propose TMIA, a novel black-box attack that leverages bidirectional LSTMs to infer temporal membership from model outputs observed across successive updates. Through extensive experiments on three language models and three image classification models, we show that TMIA is highly effective and significantly outperforms existing baselines. Finally, we evaluate three potential defenses, revealing the trade-off between privacy protection and model utility.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage

    Mar 25, 2026Faiz Taleb, Ivan Gazeau, Maryline LaurentUser Attribute Inference AttacksMembership Inference Attacks

  2. Sequential Membership Inference Attacks

    Feb 18, 2026Thomas Michel, Debabrota Basu, Emilie KaufmannMembership Inference AttacksPrivacy Auditing