Rényi Pufferfish Privacy with Gaussian-based Priors: From Single Gaussian to Mixture Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Wenjin, Ding, Ni, Zhang, Zijian, Li, Zhen, Sun, Jing, An, Jincheng, Liu, Yong, Zhu, Liehuang
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910167026630656
author Yang, Wenjin
Ding, Ni
Zhang, Zijian
Li, Zhen
Sun, Jing
An, Jincheng
Liu, Yong
Zhu, Liehuang
author_facet Yang, Wenjin
Ding, Ni
Zhang, Zijian
Li, Zhen
Sun, Jing
An, Jincheng
Liu, Yong
Zhu, Liehuang
contents Rényi Pufferfish Privacy (RPP) provides a Rényi divergence-based privacy framework for correlated data, but existing $\infty$-Wasserstein mechanisms are often conservative and sacrifice data utility. We study Gaussian mechanisms for RPP under Gaussian and Gaussian-mixture priors. For single Gaussian priors, we derive the exact Rényi divergence after Gaussian perturbation, obtain a relaxed closed-form sufficient condition for $(α,ε)$-RPP, and characterize the monotonicity of the calibrated noise with respect to the privacy budget $ε$ and the Rényi order $α$. To handle more general non-Gaussian and multimodal priors, we approximate secret-conditioned outputs with Gaussian mixture models and introduce an optimal-transport-based sufficient condition for RPP. Experiments on three UCI datasets with statistical (\textsc{RAW}, \textsc{MEAN}) and model-output (\textsc{BNN}, \textsc{GP}) queries show that our prior-aware mechanisms consistently require less noise than a recent RPP additive-noise baseline, achieving an average noise reduction of 48.9\%. These results show that our mechanisms can substantially improve the privacy-utility trade-off under RPP.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23649
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rényi Pufferfish Privacy with Gaussian-based Priors: From Single Gaussian to Mixture Model
Yang, Wenjin
Ding, Ni
Zhang, Zijian
Li, Zhen
Sun, Jing
An, Jincheng
Liu, Yong
Zhu, Liehuang
Cryptography and Security
Rényi Pufferfish Privacy (RPP) provides a Rényi divergence-based privacy framework for correlated data, but existing $\infty$-Wasserstein mechanisms are often conservative and sacrifice data utility. We study Gaussian mechanisms for RPP under Gaussian and Gaussian-mixture priors. For single Gaussian priors, we derive the exact Rényi divergence after Gaussian perturbation, obtain a relaxed closed-form sufficient condition for $(α,ε)$-RPP, and characterize the monotonicity of the calibrated noise with respect to the privacy budget $ε$ and the Rényi order $α$. To handle more general non-Gaussian and multimodal priors, we approximate secret-conditioned outputs with Gaussian mixture models and introduce an optimal-transport-based sufficient condition for RPP. Experiments on three UCI datasets with statistical (\textsc{RAW}, \textsc{MEAN}) and model-output (\textsc{BNN}, \textsc{GP}) queries show that our prior-aware mechanisms consistently require less noise than a recent RPP additive-noise baseline, achieving an average noise reduction of 48.9\%. These results show that our mechanisms can substantially improve the privacy-utility trade-off under RPP.
title Rényi Pufferfish Privacy with Gaussian-based Priors: From Single Gaussian to Mixture Model
topic Cryptography and Security
url https://arxiv.org/abs/2604.23649