Access Control with Encrypted Feature Maps for Object Detection Models

TL;DR

This paper introduces a novel access control method for object detection models that encrypts feature maps with a secret key, ensuring high performance for authorized users while degrading it for unauthorized ones.

Contribution

It is the first to propose encrypting feature maps for access control in object detection models, enhancing security without sacrificing accuracy for authorized users.

Findings

Authorized users achieve near non-protected model performance.

The method effectively degrades performance for unauthorized users.

Robustness against unauthorized access is demonstrated.

Abstract

In this paper, we propose an access control method with a secret key for object detection 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 detection performance to authorized users but to also degrade the performance for unauthorized users. The use of transformed images was proposed for the access control of image classification models, but these images cannot be used for object detection models 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.