Access Control of Semantic Segmentation Models Using Encrypted Feature Maps

TL;DR

This paper introduces a novel access control method for semantic segmentation models that encrypts feature maps with a secret key, ensuring authorized users maintain high performance while unauthorized users cannot benefit from the model.

Contribution

It presents the first method to control access to semantic segmentation models by encrypting feature maps, addressing limitations of image encryption methods.

Findings

Authorized users achieve near-original segmentation performance.

Unauthorized users cannot access model benefits without the secret key.

The method is robust against unauthorized access.

Abstract

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.