论文标题
通过随机参与联合学习的隐私放大
Privacy Amplification via Random Participation in Federated Learning
论文作者
论文摘要
在子采样数据集上运行随机算法，而不是整个数据集放大差异隐私保证。在这项工作中，在联合环境中，除了对其本地数据集进行了采样，我们考虑了客户的随机参与。由于客户的这种随机参与会在同一客户端的子采样中创建相关性，因此我们通过非均匀的子采样分析相应的隐私放大。我们表明，当本地数据集的大小很小时，通过随机参与的隐私保证与集中设置的隐私保证，其中整个数据集位于单个主机中并进行了二次采样。另一方面，当本地数据集很大时，观察该算法的输出可能会以很高的信心披露采样客户的身份。我们的分析表明，即使在这种情况下，通过随机参与仅通过本地亚采样来保证的隐私也优于这些隐私。
Running a randomized algorithm on a subsampled dataset instead of the entire dataset amplifies differential privacy guarantees. In this work, in a federated setting, we consider random participation of the clients in addition to subsampling their local datasets. Since such random participation of the clients creates correlation among the samples of the same client in their subsampling, we analyze the corresponding privacy amplification via non-uniform subsampling. We show that when the size of the local datasets is small, the privacy guarantees via random participation is close to those of the centralized setting, in which the entire dataset is located in a single host and subsampled. On the other hand, when the local datasets are large, observing the output of the algorithm may disclose the identities of the sampled clients with high confidence. Our analysis reveals that, even in this case, privacy guarantees via random participation outperform those via only local subsampling.
