Access Control of Semantic Segmentation Models Using Encrypted Feature Maps
This addresses the need for model protection in semantic segmentation applications, offering a practical solution for controlling access to trained models.
The paper tackles the problem of unauthorized use of semantic segmentation models by proposing an access control method that encrypts selected feature maps with a secret key, allowing authorized users to achieve nearly the same performance as non-protected models while degrading performance for unauthorized users.
In this paper, we propose an access control method with a secret key for semantic segmentation models for the first time so that unauthorized users without a secret key cannot benefit from the performance of trained models. The method enables us not only to provide a high segmentation performance to authorized users but to also degrade the performance for unauthorized users. We first point out that, for the application of semantic segmentation, conventional access control methods which use encrypted images for classification tasks are not directly applicable due to performance degradation. Accordingly, in this paper, selected feature maps are encrypted with a secret key for training and testing models, instead of input images. In an experiment, the protected models allowed authorized users to obtain almost the same performance as that of non-protected models but also with robustness against unauthorized access without a key.