We propose a novel method for privacy-preserving deep neural networks (DNNs) with the Vision Transformer (ViT). The method allows us not only to train models and test with visually protected images but to also avoid the performance degradation caused from the use of encrypted images, whereas conventional methods cannot avoid the influence of image encryption. A domain adaptation method is used to efficiently fine-tune ViT with encrypted images. In experiments, the method is demonstrated to outperform conventional methods in an image classification task on the CIFAR-10 and ImageNet datasets in terms of classification accuracy.

翻译：我们提出了一种面向隐私保护深度神经网络（DNN）的新方法，该方法基于视觉Transformer（Vision Transformer, ViT）架构。该方法不仅能够使用视觉保护图像进行模型训练与测试，还能避免因使用加密图像导致的性能下降，而传统方法无法规避图像加密带来的负面影响。通过引入领域自适应技术，我们实现了对ViT在加密图像上的高效微调。实验结果表明，在CIFAR-10和ImageNet数据集上的图像分类任务中，该方法在分类准确率方面优于传统方法。