论文标题
使用基于流动的深层生成模型的局部差异隐私图像生成
Local Differential Privacy Image Generation Using Flow-based Deep Generative Models
论文作者
论文摘要
诊断放射科医生需要人工智能（AI）进行医学成像，但是在AI中培训所需的医学图像的访问已变得越来越限制。要释放和使用医学图像，我们需要一种可以同时保护隐私并保存医学图像中的病理的算法。为了开发这样的算法，我们提出了DP-Glow，即当地差异隐私（LDP）算法的混合物和基于流动的深层生成模型（GLOW）之一。通过应用发光模型，我们将图像的PixelWise相关性解散，这使得很难使用直接的LDP算法来保护隐私。具体而言，我们将图像映射到发光模型的潜在向量上，其每个元素都遵循独立的正态分布，然后将拉普拉斯机理应用于潜在矢量。此外，我们将DP-Glow应用于胸部X射线图像，以在保留病理时生成LDP图像。
Diagnostic radiologists need artificial intelligence (AI) for medical imaging, but access to medical images required for training in AI has become increasingly restrictive. To release and use medical images, we need an algorithm that can simultaneously protect privacy and preserve pathologies in medical images. To develop such an algorithm, here, we propose DP-GLOW, a hybrid of a local differential privacy (LDP) algorithm and one of the flow-based deep generative models (GLOW). By applying a GLOW model, we disentangle the pixelwise correlation of images, which makes it difficult to protect privacy with straightforward LDP algorithms for images. Specifically, we map images onto the latent vector of the GLOW model, each element of which follows an independent normal distribution, and we apply the Laplace mechanism to the latent vector. Moreover, we applied DP-GLOW to chest X-ray images to generate LDP images while preserving pathologies.
