Protecting Semantic Segmentation Models by Using Block-wise Image Encryption with Secret Key from Unauthorized Access

07/20/2021
by   Hiroki Ito, et al.
0

Since production-level trained deep neural networks (DNNs) are of a great business value, protecting such DNN models against copyright infringement and unauthorized access is in a rising demand. However, conventional model protection methods focused only the image classification task, and these protection methods were never applied to semantic segmentation although it has an increasing number of applications. In this paper, we propose to protect semantic segmentation models from unauthorized access by utilizing block-wise transformation with a secret key for the first time. Protected models are trained by using transformed images. Experiment results show that the proposed protection method allows rightful users with the correct key to access the model to full capacity and deteriorate the performance for unauthorized users. However, protected models slightly drop the segmentation performance compared to non-protected models.

READ FULL TEXT

page 3

page 4

page 5

research
09/03/2021

Access Control Using Spatially Invariant Permutation of Feature Maps for Semantic Segmentation Models

In this paper, we propose an access control method that uses the spatial...
research
05/31/2021

A Protection Method of Trained CNN Model with Secret Key from Unauthorized Access

In this paper, we propose a novel method for protecting convolutional ne...
research
11/17/2021

Protection of SVM Model with Secret Key from Unauthorized Access

In this paper, we propose a block-wise image transformation method with ...
research
06/11/2022

Access Control of Semantic Segmentation Models Using Encrypted Feature Maps

In this paper, we propose an access control method with a secret key for...
research
08/28/2022

An Access Control Method with Secret Key for Semantic Segmentation Models

A novel method for access control with a secret key is proposed to prote...
research
03/05/2021

Transfer Learning-Based Model Protection With Secret Key

We propose a novel method for protecting trained models with a secret ke...
research
09/01/2021

A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Access

In this paper, we propose a model protection method for convolutional ne...

Please sign up or login with your details

Forgot password? Click here to reset