We explore Reconstruction Robustness (ReRo), which was recently proposed as an upper bound on the success of data reconstruction attacks against machine learning models. Previous research has demonstrated that differential privacy (DP) mechanisms also provide ReRo, but so far, only asymptotic Monte Carlo estimates of a tight ReRo bound have been shown. Directly computable ReRo bounds for general DP mechanisms are thus desirable. In this work, we establish a connection between hypothesis testing DP and ReRo and derive closed-form, analytic or numerical ReRo bounds for the Laplace and Gaussian mechanisms and their subsampled variants.

翻译：我们探索了最近提出的重建鲁棒性（ReRo），该指标用于界定针对机器学习模型的数据重建攻击成功率的上界。先前的研究表明，差分隐私（DP）机制同样能提供ReRo保证，但迄今为止，仅有渐近蒙特卡洛估计的严格ReRo上界被证明。因此，针对通用DP机制的直接可计算ReRo上界是值得期待的。在本工作中，我们建立了假设检验DP与ReRo之间的关联，并为拉普拉斯机制、高斯机制及其子采样变体推导出闭式、解析或数值形式的ReRo上界。