Privacy-Preserving Semantic Segmentation without Key Management
Addresses privacy concerns in semantic segmentation for clients who need to protect their image data without sharing encryption keys.
The paper proposes a privacy-preserving semantic segmentation method that allows each client to use independent keys for encryption, eliminating the need for key management. Experiments on Cityscapes with a vision transformer model (SETR) confirm its effectiveness.
This paper proposes a novel privacy-preserving semantic segmentation method that can use independent keys for each client and image. In the proposed method, the model creator and each client encrypt images using locally generated keys, and model training and inference are conducted on the encrypted images. To mitigate performance degradation, an image encryption method is applied to model training in addition to the generation of test images. In experiments, the effectiveness of the proposed method is confirmed on the Cityscapes dataset under the use of a vision transformer-based model, called SETR.