arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.04739cs.CR
收藏

黑箱环境下Rényi差分隐私的下界

Lower Bounds for Rényi Differential Privacy in a Black-Box Setting

Tim Kutta, Önder Askin, Martin Dunsche

摘要:

我们提出了新的方法来评估隐私保证的算法方面雷尼差分隐私。据我们所知,这项工作是第一个在黑盒场景中解决这个问题的工作,其中只有算法输出可用。为了量化隐私泄露,我们设计了一个新的估计一对输出分布的Rényi分歧。这个估计量被转换成一个统计下限,被证明是持有大样本的高概率。我们的方法适用于广泛的算法,包括许多著名的例子,从隐私文献。我们证明了我们的方法的有效性,实验包括算法和隐私增强的方法,还没有被认为是在相关的作品。

英文摘要:

We present new methods for assessing the privacy guarantees of an algorithm with regard to Rényi Differential Privacy. To the best of our knowledge, this work is the first to address this problem in a black-box scenario, where only algorithmic outputs are available. To quantify privacy leakage, we devise a new estimator for the Rényi divergence of a pair of output distributions. This estimator is transformed into a statistical lower bound that is proven to hold for large samples with high probability. Our method is applicable for a broad class of algorithms, including many well-known examples from the privacy literature. We demonstrate the effectiveness of our approach by experiments encompassing algorithms and privacy enhancing methods that have not been considered in related works.

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。

↑