论文标题
基于云的少量学习的隐私增强
Privacy Enhancement for Cloud-Based Few-Shot Learning
论文作者
论文摘要
对于准确的模型，需要更少的数据，很少有射击学习表现出许多应用程序域中的鲁棒性和一般性。但是，在不信任的环境中部署很少的模型可能会引起隐私问题，例如攻击或对手，可能会违反用户供用数据的隐私。本文通过建立一种新颖的隐私嵌入空间来维护数据的隐私空间，从而在不信任的环境中研究了少量学习的隐私增强，以保留数据的隐私并保持模型的准确性。我们研究了各种图像隐私方法的影响，例如模糊，像素化，高斯噪声和差异化私有像素化（DP-pix）对少量图像分类的影响，并提出了一种通过关节损失来学习隐私表示表示的方法。经验结果表明，如何为隐私增强的少数学习而谈判如何进行隐私绩效权衡。
Requiring less data for accurate models, few-shot learning has shown robustness and generality in many application domains. However, deploying few-shot models in untrusted environments may inflict privacy concerns, e.g., attacks or adversaries that may breach the privacy of user-supplied data. This paper studies the privacy enhancement for the few-shot learning in an untrusted environment, e.g., the cloud, by establishing a novel privacy-preserved embedding space that preserves the privacy of data and maintains the accuracy of the model. We examine the impact of various image privacy methods such as blurring, pixelization, Gaussian noise, and differentially private pixelization (DP-Pix) on few-shot image classification and propose a method that learns privacy-preserved representation through the joint loss. The empirical results show how privacy-performance trade-off can be negotiated for privacy-enhanced few-shot learning.
