论文标题
DPD-Infogan：差异性私有分布式Infogan
DPD-InfoGAN: Differentially Private Distributed InfoGAN
论文作者
论文摘要
生成对抗网络（GAN）是能够生成合成数据集的深度学习体系结构。尽管产生了高质量的合成图像，但默认的gan仍无法控制其生成的图像类型。最大化GAN（INFOGAN）的信息是默认GAN的一个变体，它引入了特征控制变量，这些变量是通过框架自动学习的，因此可以更好地控制所产生的不同图像。由于INFOGAN的模型复杂性很高，因此生成分布往往集中在训练数据点周围。这是一个关键的问题，因为模型可能会无意间暴露于数据集中存在的敏感和私人信息。为了解决这个问题，我们提出了一个差异化的Infogan（DP-Infogan）。我们还将框架扩展到分布式设置（DPD-INFOGAN），以允许客户以隐私性的方式学习其他客户端数据集中存在的不同属性。在我们的实验中，我们证明了DP-Infogan和DPD-Infogan均可合成具有对图像属性的灵活控制的高质量图像，同时保留隐私。
Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN has no control over the kinds of images it generates. The Information Maximizing GAN (InfoGAN) is a variant of the default GAN that introduces feature-control variables that are automatically learned by the framework, hence providing greater control over the different kinds of images produced. Due to the high model complexity of InfoGAN, the generative distribution tends to be concentrated around the training data points. This is a critical problem as the models may inadvertently expose the sensitive and private information present in the dataset. To address this problem, we propose a differentially private version of InfoGAN (DP-InfoGAN). We also extend our framework to a distributed setting (DPD-InfoGAN) to allow clients to learn different attributes present in other clients' datasets in a privacy-preserving manner. In our experiments, we show that both DP-InfoGAN and DPD-InfoGAN can synthesize high-quality images with flexible control over image attributes while preserving privacy.
