Metraipolis › archive › dc_efdab4863ee8
Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches — arXiv:2610.42139
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.42139
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:10:53.269Z
- SHA-256 of the archived text
78a2ebfb52a5557fce798af6cfbee6144a261770498157bc748e9754a7fe132c- Stable URL of this page
https://metraipolis.com/documento/dc_efdab4863ee8
How to cite
Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches — arXiv:2610.42139 — arXiv (en), https://arxiv.org/abs/2610.42139 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efdab4863ee8 (Metraipolis archive dc_efdab4863ee8, sha256 78a2ebfb52a5557fce798af6cfbee6144a261770498157bc748e9754a7fe132c)
BibTeX
@misc{dcefdab4863ee8,
title = {Counting on Dummies: Privacy Amplification with Observable Counts and Truncated Batches — arXiv:2610.42139},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.42139},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efdab4863ee8; sha256 78a2ebfb52a5557fce798af6cfbee6144a261770498157bc748e9754a7fe132c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42139. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In many practical deployments of Differentially Private Stochastic Gradient Descent (DP-SGD), the server processes data in batches. Randomly sampling these batches allows for better privacy bounds via privacy amplification results. Most sampling schemes with provable privacy amplification, including Poisson sampling and random allocation, result in variable batch sizes. The privacy guarantee of these schemes requires that the batch sizes are not revealed. In distributed settings, the server performing the aggregation or any party observing the communication traffic may learn these batch sizes. Furthermore, in both centralized and distributed settings, memory and computation constraints may require each batch to be of some maximum size $s$, necessitating truncation of the batch when it exceeds this limit. It is known that this truncation can result in a significant increase in privacy loss. In this work, we address both of these challenges via a simple mechanism that uses a random number of \emph{dummy points} to privatize the batch size and maintain the privacy guarantee even under truncation. We demonstrate that our mechanism is easy to implement in a distributed setting, and provide a general analysis of this mechanism for both Poisson sampling and random allocation. Our analysis is designed to support efficient and relatively tight privacy accounting. It also effectively amplifies the privacy of the count releases by subsampling, making the expected number of dummy points asymptotically smaller than what is needed to directly privatize the (sensitivity-one) batch sizes with non-negative noise. For Poisson sampling with truncated batches, we demonstrate empirically that our mechanism achieves better privacy--efficiency tradeoffs than the direct accounting for truncation recently given by (Ganesh, 2025).
Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.42139 — 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 2026-11-03T08:02:08.789Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).