论文标题
强大的隐私和公用事业保证：空中统计估算
Strong Privacy and Utility Guarantee: Over-the-Air Statistical Estimation
论文作者
论文摘要
我们考虑了分布式数据的统计估计的隐私问题，在该数据中，用户通过高斯多访问通道（MAC）与中央处理器进行通信。为了避免在数字传输方案中不可避免地牺牲数据实用性为隐私牺牲，我们设计了一种充电估算策略，该策略利用了MAC渠道的附加性。使用通道输出和用户数据之间的共同信息作为度量，我们获得了我们计划的隐私范围，并验证它可以保证强大的隐私而不会产生更大的估计错误。此外，为了提高方法的鲁棒性，我们通过在本地添加高斯噪声来调整主要方案，并在条件相互信息约束下得出相应的minimax均方根误差。将我们的方法的性能与数字化的性能进行比较，我们表明，最小值误差通常会减少$ O（\ frac {1} {n}）$，这表明了空中估算可保留数据隐私和实用性的优势。
We consider the privacy problem of statistical estimation from distributed data, where users communicate to a central processor over a Gaussian multiple-access channel(MAC). To avoid the inevitable sacrifice of data utility for privacy in digital transmission schemes, we devise an over-the-air estimation strategy which utilizes the additive nature of MAC channel. Using the mutual information between the channel outputs and users' data as the metric, we obtain the privacy bounds for our scheme and validate that it can guarantee strong privacy without incurring larger estimation error. Further, to increase the robustness of our methods, we adjust our primary schemes by adding Gaussian noises locally and derive the corresponding minimax mean squared error under conditional mutual information constraints. Comparing the performance of our methods to the digital ones, we show that the minimax error decreases by $O(\frac{1}{n})$ in general, which suggests the advantages of over-the-air estimation for preserving data privacy and utility.
