Metraipolis › archive › dc_58f71f89d30d
Timing is Everything: Inferring Temporal Membership in Continually Updated Models — arXiv:2611.05781
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.05781
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-05T18:21:01.998Z
- SHA-256 of the archived text
8a00236eb8cbe06f7e409bdf42a627f418c0f2ca1a55e7fd7f8c85cec13e20b1- Stable URL of this page
https://metraipolis.com/documento/dc_58f71f89d30d
How to cite
Timing is Everything: Inferring Temporal Membership in Continually Updated Models — arXiv:2611.05781 — arXiv (en), https://arxiv.org/abs/2611.05781 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58f71f89d30d (Metraipolis archive dc_58f71f89d30d, sha256 8a00236eb8cbe06f7e409bdf42a627f418c0f2ca1a55e7fd7f8c85cec13e20b1)
BibTeX
@misc{dc58f71f89d30d,
title = {Timing is Everything: Inferring Temporal Membership in Continually Updated Models — arXiv:2611.05781},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.05781},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58f71f89d30d; sha256 8a00236eb8cbe06f7e409bdf42a627f418c0f2ca1a55e7fd7f8c85cec13e20b1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05781. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.05781 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-05T18:15:18.883Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).