Abstract
In recent years, privacy-preserving methods for deep learning have become an urgent problem. Accordingly, we propose the combined use of federated learning (FL) and encrypted images for privacy-preserving image classification under the use of the vision transformer (ViT). The proposed method allows us not only to train models over multiple participants without directly sharing their raw data but to also protect the privacy of test (query) images for the first time. In addition, it can also maintain the same accuracy as normally trained models. In an experiment, the proposed method was demonstrated to well work without any performance degradation on the CIFAR-10 and CIFAR-100 datasets.
Abstract (translated)
近年来,深度学习中的隐私保护方法已成为一个紧迫的问题。因此,我们提出了在视觉Transformer(ViT)的使用下,将联邦学习(FL)和加密图像用于隐私保护图像分类的方法。该方法不仅可以在多个参与者之间直接共享原始数据的情况下训练模型,而且可以首次保护测试(查询)图像的隐私。此外,它还与通常训练的模型保持相同的精度。在一个实验中,该方法在CIFAR-10和CIFAR-100数据集上证明了良好的工作,没有性能下降。
URL
https://arxiv.org/abs/2301.09255
