Metraipolis › archive › dc_fd6076903dbb

Exploring the Privacy--Size Tradeoff for Differentially Private Self-Attentive Variational Autoencoders — arXiv:2611.05582

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05582
License (as archived)
CC0-1.0
Archived
2026-11-05T18:21:10.091Z
SHA-256 of the archived text
cc72f4fcfb5a966f73e0a6904552f2ebf743f7748f3db31626f43f86f06a1fdf
Stable URL of this page
https://metraipolis.com/documento/dc_fd6076903dbb

How to cite

Exploring the Privacy--Size Tradeoff for Differentially Private Self-Attentive Variational Autoencoders — arXiv:2611.05582 — arXiv (en), https://arxiv.org/abs/2611.05582 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd6076903dbb (Metraipolis archive dc_fd6076903dbb, sha256 cc72f4fcfb5a966f73e0a6904552f2ebf743f7748f3db31626f43f86f06a1fdf)
BibTeX
@misc{dcfd6076903dbb,
  title = {Exploring the Privacy--Size Tradeoff for Differentially Private Self-Attentive Variational Autoencoders — arXiv:2611.05582},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05582},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd6076903dbb; sha256 cc72f4fcfb5a966f73e0a6904552f2ebf743f7748f3db31626f43f86f06a1fdf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05582. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data tends to be most useful when it is shared, and the data most worth sharing is often the data that privacy obligations restrict. Synthetic data from a generator trained under differential privacy (DP) is one way to reconcile the two, but its utility depends on the privacy budget $\varepsilon$ and on how much data the generator sees - a parameter that most data sharing applications of synthetic data control. We present SAVANT, a self-attentive variational autoencoder for tabular data trained with DP-SGD that, to our knowledge, is the first to combine attention, a VAE, and DP in one tabular model. We evaluate it against two marginal mechanisms, PrivBayes and MST, jointly over the privacy budget and the dataset size on two public datasets, measuring the utility a downstream classifier loses by training on synthetic rather than real data. We find that, under the same DP guarantee, more data generally means more utility. For the marginal mechanisms it absorbs most of what a strict budget costs, and a noise-scaling argument suggests DP-SGD exchanges data fo budget at a worse rate. Two independent membership-inference attacks, judged against a measured null, found no aggregate membership signal.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Engineering, Finance, and Science (cs.CE); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2611.05582 — 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 2026-11-05T18:15:18.892Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).