arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.05723cs.CR
收藏

$α$-Wasserstein机制用于Rényi Pufferfish隐私

$α$-Wasserstein Mechanism for Rényi Pufferfish Privacy

Ni Ding, Wenjin Yang, Zijian Zhang

AI总结:

本文提出$α$-Wasserstein机制,通过拉普拉斯和高斯噪声实现Rényi Pufferfish隐私,利用霍尔德不等式校准参数,证明其在$(α, ε)$隐私下优于传统方法,且高斯机制在效用上更优。

摘要:

本文介绍了一种$α$-Wasserstein机制,用于通过拉普拉斯和高斯噪声实现Rényi Pufferfish隐私。通过利用霍尔德不等式,我们证明拉普拉斯机制的尺度参数可通过$W_α$度量的上界校准,以满足$(α, ε)$-Rényi Pufferfish隐私,其中$α∈(1, ∞]$。我们证明在极限$α=∞$时,该框架恢复了已知的$W_∞$机制用于$ε$-pufferfish隐私。此结果随后扩展到指数机制。此外,我们提出了适用于高斯噪声的$W_α$机制,证明其在Rényi差分隐私框架内扩展了现有结果。实验评估表明,我们的$α$-Wasserstein机制相比传统$W_∞$方法显著降低了噪声功率,且高斯机制在效用上优于拉普拉斯机制。值得注意的是,本文推导的机制实现了精确的$(α, ε)$-Rényi Pufferfish隐私,而无需额外的放松,如$δ$-近似。

英文摘要:

This paper introduces the $α$-Wasserstein mechanism for achieving Rényi Pufferfish Privacy using Laplace and Gaussian noise. By leveraging Hölder's inequality, we demonstrate that the scale parameter of the Laplace mechanism can be calibrated via an upper bound on the $W_α$ metric to satisfy $(α, ε)$-Rényi Pufferfish Privacy for $α\in (1, \infty]$. We show that at the limit $α= \infty$, this framework recovers the established $W_\infty$ mechanism for $ε$-pufferfish privacy. This result is subsequently extended to the exponential mechanism. Furthermore, we propose a $W_α$ mechanism for Gaussian noise for $α\in (1, \infty)$, demonstrating that it generalizes existing results within the Rényi Differential Privacy framework. Experimental evaluations reveal that our $α$-Wasserstein mechanism significantly reduces noise power compared to the conventional $W_\infty$-based approach, with the Gaussian mechanism providing superior utility over the Laplace mechanism. Notably, the mechanisms derived in this work achieve exact $(α, ε)$-Rényi Pufferfish Privacy without requiring additional relaxations, such as $δ$-approximations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑