Privacy-Preserving Image Sharing Via Sparsifying Layers on Convolutional Groups
Privacy-Preserving Image Sharing Via Sparsifying Layers on Convolutional Groups
复制标题
DOI：
10.1109/icassp40776.2020.9054046
复制
发表时间：
2020-02
期刊：
影响因子：
--
通讯作者：
Sohrab Ferdowsi;Behrooz Razeghi;T. Holotyak;F. Calmon;S. Voloshynovskiy
中科院分区：
文献类型：
--
作者：
Sohrab Ferdowsi;Behrooz Razeghi;T. Holotyak;F. Calmon;S. Voloshynovskiy
我们提出了一个实用的框架来解决大规模设置中的隐私感知图像共享问题。我们认为，虽然紧凑性总是希望在规模，这种需要是更严重的，当试图进一步保护隐私敏感的内容。因此，我们对图像进行编码，这样，一方面，表示存储在公共领域，而无需支付隐私保护的巨大成本，但模糊，因此不会从图像中泄漏可辨别的内容，除非攻击者可以使用组合昂贵的猜测机制。另一方面，授权用户被提供有可以容易地保持安全的非常紧凑的密钥。这可以用于消除歧义并忠实地重建相应的访问授权图像。我们通过我们设计的卷积自动编码器实现了这一点，其中特征图通过稀疏化变换独立传递，提供多个紧凑代码，每个代码负责重建图像的不同属性。该框架在一个大型图像数据库上进行了测试，并提供了公共实现。
We propose a practical framework to address the problem of privacy-aware image sharing in large-scale setups. We argue that, while compactness is always desired at scale, this need is more severe when trying to furthermore protect the privacy-sensitive content. We therefore encode images, such that, from one hand, representations are stored in the public domain without paying the huge cost of privacy protection, but ambiguated and hence leaking no discernible content from the images, unless a combinatorially-expensive guessing mechanism is available for the attacker. From the other hand, authorized users are provided with very compact keys that can easily be kept secure. This can be used to disambiguate and reconstruct faithfully the corresponding access-granted images. We achieve this with a convolutional autoencoder of our design, where feature maps are passed independently through sparsifying transformations, providing multiple compact codes, each responsible for reconstructing different attributes of the image. The framework is tested on a large-scale database of images with public implementation available.