Recent work argues for using Gaussian differential privacy (GDP) to report the privacy guarantees in privacy-preserving machine learning. We provide principled mappings from pure-DP $\varepsilon$ to GDP $μ$ by matching the worst-case success of a strong-adversary membership inference attack in terms of three metrics: multiplicative advantage at fixed FPR, precision at fixed recall, and the standard privacy profile. We tabulate $μ$ values across a useful range of parameters and recommend $μ\approx \varepsilon/5$ as a conservative general-purpose conversion.

翻译：近期研究主张采用高斯差分隐私（GDP）来报告隐私保护机器学习中的隐私保证。我们通过匹配强敌手成员推断攻击在最坏情况下的成功程度（涉及三种度量指标：固定虚警率下的乘法优势、固定召回率下的精确度以及标准隐私轮廓），给出了从纯-DP $\varepsilon$ 到 GDP $μ$ 的具有原则性的映射。我们在一个有用的参数范围内列出了 $μ$ 值的表格，并推荐 $μ\approx \varepsilon/5$ 作为保守的通用转换。