Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation
Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation
复制标题
DOI：
10.1145/3461702.3462625
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Chris Waites;Rachel Cummings
中科院分区：
文献类型：
--
作者：
Chris Waites;Rachel Cummings
归一化流模型已经成为密度估计问题的一种流行解决方案，可以生成高质量的合成数据以及精确的概率密度评估。然而，在个人与训练数据直接相关的环境中，发布这样的模型会引起隐私问题。在这项工作中，我们提出使用提供显式差分隐私保证的规范化流模型作为解决隐私保护密度估计问题的新方法。我们使用基准数据集来评估我们方法的有效性，并证明我们的方法实质上优于以前最先进的方法。我们还展示了如何将我们的算法应用于差分私有异常检测任务。
Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are directly associated with the training data, releasing such a model raises privacy concerns. In this work, we propose the use of normalizing flow models that provide explicit differential privacy guarantees as a novel approach to the problem of privacy-preserving density estimation. We evaluate the efficacy of our approach empirically using benchmark datasets, and we demonstrate that our method substantially outperforms previous state-of-the-art approaches. We additionally show how our algorithm can be applied to the task of differentially private anomaly detection.