论文标题
隐私神经网络及其安全评估的图像转换网络
Image Transformation Network for Privacy-Preserving Deep Neural Networks and Its Security Evaluation
论文作者
论文摘要
我们提出了一个转换网络，用于为隐私保护DNN生成视觉保护图像。提出的转换网络是通过使用普通图像数据集训练的，以便将普通图像转换为视觉保护图像。常规的感知加密方法在图像分类中具有较弱的视觉保护性能和一些准确性降解。相比之下，提出的网络不仅使我们能够强烈保护视觉信息，还可以维持使用普通图像实现的图像分类精度。在图像分类实验中，建议的网络被证明是为了强烈保护普通图像上的视觉信息，而不会在使用CIFAR数据集中进行任何性能降低。此外，可以证明，在实验中，视觉保护图像对基于DNN的攻击（称为逆变换网络攻击（ITN-攻击））是可靠的。
We propose a transformation network for generating visually-protected images for privacy-preserving DNNs. The proposed transformation network is trained by using a plain image dataset so that plain images are transformed into visually protected ones. Conventional perceptual encryption methods have a weak visual-protection performance and some accuracy degradation in image classification. In contrast, the proposed network enables us not only to strongly protect visual information but also to maintain the image classification accuracy that using plain images achieves. In an image classification experiment, the proposed network is demonstrated to strongly protect visual information on plain images without any performance degradation under the use of CIFAR datasets. In addition, it is shown that the visually protected images are robust against a DNN-based attack, called inverse transformation network attack (ITN-Attack) in an experiment.
