Access Control of Object Detection Models Using Encrypted Feature Maps
This work addresses access control for object detection models, which is incremental as it applies an existing method to a new model type.
The paper tackled the problem of extending encrypted feature map access control to object detection models, demonstrating its effectiveness for the first time in this domain.
In this paper, we propose an access control method for object detection models. The use of encrypted images or encrypted feature maps has been demonstrated to be effective in access control of models from unauthorized access. However, the effectiveness of the approach has been confirmed in only image classification models and semantic segmentation models, but not in object detection models. In this paper, the use of encrypted feature maps is shown to be effective in access control of object detection models for the first time.