论文标题
用内核量子rényi发散在高维度中审核差异隐私
Auditing Differential Privacy in High Dimensions with the Kernel Quantum Rényi Divergence
论文作者
论文摘要
差异隐私（DP）是私人数据发布和私人机器学习的事实上的标准。审核黑盒DP算法和机制以证明它们是否满足某些DP保证是具有挑战性的，尤其是在高维度上。我们根据概率分布的新差异提出放松差异隐私的放松：内核RényiDivergence及其正则化版本。我们表明，即使在高维度中，也可以从样本中估算正规内核rényi的分歧，从而为$ \ varepsilon $ -dp，$（\ varepsilon，δ）$ - dp and $（α，\ varepsilon）$ \ varepsilon $ -dp产生审计程序。
Differential privacy (DP) is the de facto standard for private data release and private machine learning. Auditing black-box DP algorithms and mechanisms to certify whether they satisfy a certain DP guarantee is challenging, especially in high dimension. We propose relaxations of differential privacy based on new divergences on probability distributions: the kernel Rényi divergence and its regularized version. We show that the regularized kernel Rényi divergence can be estimated from samples even in high dimensions, giving rise to auditing procedures for $\varepsilon$-DP, $(\varepsilon,δ)$-DP and $(α,\varepsilon)$-Rényi DP.
