arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1910.02007cs.LGstat.ML
收藏

PPGAN:隐私保护的生成对抗网络

PPGAN: Privacy-preserving Generative Adversarial Network

Heilongjiang University(黑龙江大学);Southern University of Science and Technology(南方科技大学)

Yi Liu, Jialiang Peng, James J. Q Yu, Yi Wu

摘要:

生成对抗网络(GAN)及其变体作为数据生成模型的完美代表,为研究人员提供了大量高质量的生成数据。它们说明了一个有希望的方向,研究有限的数据可用性。当GAN从数据集中学习语义丰富的数据分布时,生成的分布的密度倾向于集中在训练数据上。由于深度神经网络的梯度参数包含了训练样本的数据分布,它们可以很容易地记住训练样本。当GAN应用于私人或敏感数据时,例如,患者的医疗记录,因为私人信息可能会泄漏。为了解决这个问题,我们提出了一个隐私保护生成对抗网络(PPGAN)模型,在该模型中,我们通过在模型学习过程中向梯度中添加精心设计的噪声来实现GANs中的差分隐私。此外,在PPGAN训练过程中引入了Moments Accountant策略,通过控制隐私丢失来提高模型的稳定性和兼容性。并给出了差分隐私策略的数学证明。通过对基准数据集的广泛案例研究,我们证明了PPGAN可以生成高质量的合成数据,同时在合理的隐私预算下保留所需的数据。

英文摘要:

Generative Adversarial Network (GAN) and its variants serve as a perfect representation of the data generation model, providing researchers with a large amount of high-quality generated data. They illustrate a promising direction for research with limited data availability. When GAN learns the semantic-rich data distribution from a dataset, the density of the generated distribution tends to concentrate on the training data. Due to the gradient parameters of the deep neural network contain the data distribution of the training samples, they can easily remember the training samples. When GAN is applied to private or sensitive data, for instance, patient medical records, as private information may be leakage. To address this issue, we propose a Privacy-preserving Generative Adversarial Network (PPGAN) model, in which we achieve differential privacy in GANs by adding well-designed noise to the gradient during the model learning procedure. Besides, we introduced the Moments Accountant strategy in the PPGAN training process to improve the stability and compatibility of the model by controlling privacy loss. We also give a mathematical proof of the differential privacy discriminator. Through extensive case studies of the benchmark datasets, we demonstrate that PPGAN can generate high-quality synthetic data while retaining the required data available under a reasonable privacy budget.

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。

↑