论文标题
带有秘密键的访问控制方法，用于语义分割模型
An Access Control Method with Secret Key for Semantic Segmentation Models
论文作者
论文摘要
提出了一种使用秘密钥匙访问控制的新方法，以保护模型免受本文未经授权的访问。我们专注于具有视觉变压器（VIT）的语义分割模型，称为分割变压器（SETR）。大多数现有的访问控制方法都集中在图像分类任务上，或者它们仅限于CNN。通过使用VIT拥有的贴片嵌入结构，可以用秘密键有效地对经过训练的模型和测试图像进行加密，然后在加密的域中执行语义分割任务。在实验中，该方法被确认提供了与使用纯图像无需任何加密的授权用户的准确性，并提供了正确的键，并且还为未经授权的用户提供了极度退化的准确性。
A novel method for access control with a secret key is proposed to protect models from unauthorized access in this paper. We focus on semantic segmentation models with the vision transformer (ViT), called segmentation transformer (SETR). Most existing access control methods focus on image classification tasks, or they are limited to CNNs. By using a patch embedding structure that ViT has, trained models and test images can be efficiently encrypted with a secret key, and then semantic segmentation tasks are carried out in the encrypted domain. In an experiment, the method is confirmed to provide the same accuracy as that of using plain images without any encryption to authorized users with a correct key and also to provide an extremely degraded accuracy to unauthorized users.
