Block Scrambling Image Encryption Used in Combination with Data Augmentation for Privacy-Preserving DNNs
This work addresses privacy concerns in image classification for users of DNNs, but it appears incremental as it builds on existing encryption and augmentation techniques.
The paper tackles the problem of privacy-preserving deep neural networks by proposing a novel learnable image encryption method based on block scrambling combined with data augmentation, which maintains high classification accuracy while enhancing robustness against attacks.
In this paper, we propose a novel learnable image encryption method for privacy-preserving deep neural networks (DNNs). The proposed method is carried out on the basis of block scrambling used in combination with data augmentation techniques such as random cropping, horizontal flip and grid mask. The use of block scrambling enhances robustness against various attacks, and in contrast, the combination with data augmentation enables us to maintain a high classification accuracy even when using encrypted images. In an image classification experiment, the proposed method is demonstrated to be effective in privacy-preserving DNNs.