arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11072cs.CR
收藏

基于差分隐私的图像混淆:从人脸图像到普通图像

Obfuscation of Images via Differential Privacy: From Facial Images to General Images

William Croft, Jörg-Rüdiger Sack, Wei Shi

摘要:

由于图像捕获设备在日常生活中的普遍性,个人的图像被常规地捕获。虽然这带来了许多好处,但它也侵犯了个人隐私。人脸图像模糊处理的一个很有前途的研究方向是k-相同的方法,它采用了数据库隐私的k-匿名的概念。然而,有一些缺陷的k-匿名性,结转到k-相同的方法,减损其实用性在实践中。在本文中,我们首先概述了这些不足之处,并讨论了它们的影响,在面部模糊的背景下。然后,我们开发了一个框架,通过该框架,我们获得了一个正式的差分私人担保生成机器学习模型中的面部图像的混淆。我们的方法提供了一个可证明的隐私保证,是不容易受到所概述的缺陷的k-相同的混淆,并产生照片般逼真的混淆输出。此外,我们通过实验比较表明,我们的方法可以实现可比的效用K-相同的混淆在图像中的有用功能的保存。此外,我们提出了一种方法来实现任何图像的差分隐私(即,不限于面部图像)。虽然将噪声添加到像素强度并不提供经由生成机器学习模型获得的高视觉质量,但它通过消除对训练模型的需要而提供更大的通用性。我们表明,我们提出的使用指数机制在这种情况下,能够提供优越的视觉质量,像素空间混淆使用拉普拉斯机制。

英文摘要:

Due to the pervasiveness of image capturing devices in every-day life, images of individuals are routinely captured. Although this has enabled many benefits, it also infringes on personal privacy. A promising direction in research on obfuscation of facial images has been the work in the k-same family of methods which employ the concept of k-anonymity from database privacy. However, there are a number of deficiencies of k-anonymity that carry over to the k-same methods, detracting from their usefulness in practice. In this paper, we first outline several of these deficiencies and discuss their implications in the context of facial obfuscation. We then develop a framework through which we obtain a formal differentially private guarantee for the obfuscation of facial images in generative machine learning models. Our approach provides a provable privacy guarantee that is not susceptible to the outlined deficiencies of k-same obfuscation and produces photo-realistic obfuscated output. In addition, we demonstrate through experimental comparisons that our approach can achieve comparable utility to k-same obfuscation in terms of preservation of useful features in the images. Furthermore, we propose a method to achieve differential privacy for any image (i.e., without restriction to facial images) through the direct modification of pixel intensities. Although the addition of noise to pixel intensities does not provide the high visual quality obtained via generative machine learning models, it offers greater versatility by eliminating the need for a trained model. We demonstrate that our proposed use of the exponential mechanism in this context is able to provide superior visual quality to pixel-space obfuscation using the Laplace mechanism.

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。

↑