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.

本文提出了一种使用秘密密钥进行访问控制的新方法，旨在保护具有Vision Transformer(即分割Transformer)的语义分割模型免受未经授权的访问。通过使用ViT所具有的patch embedding结构，训练模型和测试图像可以使用密钥进行有效加密，然后在加密域中执行语义分割任务。在实验中，该方法被证实在授权用户使用正确密钥的情况下提供与使用未加密的纯图像相同的准确性，并向未经授权的用户提供极度降低的准确性。

一种含密钥的语义分割模型访问控制方法