arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14068cs.LGcs.AIcs.CRcs.DSstat.ML
收藏

用于隐私保护密度估计的差分隐私规范化流

Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation

Stanford University(斯坦福大学);Columbia University(哥伦比亚大学);Georgia Institute of Technology(佐治亚理工学院)

Chris Waites, Rachel Cummings

摘要:

标准化流模型已经成为密度估计问题的流行解决方案,能够生成高质量的合成数据以及精确的概率密度估计。然而,在个人直接与训练数据相关联的情况下,发布这样的模型会引起隐私问题。在这项工作中,我们提出了使用规范化的流模型,提供明确的差分隐私保证作为一种新的方法来保护隐私的密度估计的问题。我们使用基准数据集经验性地评估了我们的方法的有效性,并且我们证明了我们的方法大大优于以前的最先进的方法。我们还展示了我们的算法可以应用到差分私有异常检测的任务。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑