An Access Control Method with Secret Key for Semantic Segmentation Models

Autor:	Nagamori, Teru, Iijima, Ryota, Kiya, Hitoshi
Rok vydání:	2022
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Cryptography and Security Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: To appear in the International Conference on Machine Learning and Cybernetics 2022 (ICMLC 2022)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2208.13135 Zobrazit plný text záznamu View this record from Arxiv