While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups remains underexplored. Existing studies have proposed methods to assess group privacy risks, but these are based on the average-case privacy risks of data records. Such approaches may underestimate the group privacy risks, thereby potentially underestimating the disparity across group privacy risks. Moreover, the current method for assessing the worst-case privacy risks of data records is time-consuming, limiting their practical applicability. To address these limitations, we introduce a novel membership inference game that can efficiently audit the approximate worst-case privacy risks of data records. Experimental results demonstrate that our method provides a more stringent measurement of group privacy risks, yielding a reliable assessment of the disparity in group privacy risks. Furthermore, to promote privacy protection fairness in DPML, we enhance the standard DP-SGD algorithm with an adaptive group-specific gradient clipping strategy, inspired by the design of canaries in differential privacy auditing studies. Extensive experiments confirm that our algorithm effectively reduces the disparity in group privacy risks, thereby enhancing the fairness of privacy protection in DPML.

翻译：尽管传统公平感知机器学习（ML）和差分隐私机器学习（DPML）已取得显著进展，但跨群体的隐私保护公平性仍未得到充分探索。现有研究提出了评估群体隐私风险的方法，但这些方法基于数据记录的平均情况隐私风险。此类方法可能低估群体隐私风险，从而可能低估跨群体隐私风险的差异。此外，当前评估数据记录最坏情况隐私风险的方法耗时严重，限制了其实际应用。为应对这些局限性，我们引入了一种新颖的成员推断博弈，能够高效审计数据记录的近似最坏情况隐私风险。实验结果表明，我们的方法提供了对群体隐私风险更为严格的度量，从而实现了对群体隐私风险差异的可靠评估。进一步地，为促进DPML中的隐私保护公平性，我们受差分隐私审计研究中金丝雀设计的启发，通过一种自适应的、针对特定群体的梯度裁剪策略，对标准DP-SGD算法进行了增强。大量实验证实，我们的算法有效降低了群体隐私风险的差异，从而提升了DPML中隐私保护的公平性。