Image and Model Transformation with Secret Key for Vision Transformer
arXiv:2207.05366 · doi:10.1587/transinf.2022MUI0001
Abstract
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key. We show for the first time that models trained with plain images can be directly transformed to models trained with encrypted images on the basis of the ViT architecture, and the performance of the transformed models is the same as models trained with plain images when using test images encrypted with the key. In addition, the proposed scheme does not require any specially prepared data for training models or network modification, so it also allows us to easily update the secret key. In an experiment, the effectiveness of the proposed scheme is evaluated in terms of performance degradation and model protection performance in an image classification task on the CIFAR-10 dataset.
arXiv comment10 pages, 5 figures
References in corpus (16)
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Intriguing properties of neural networks
- MLP-Mixer: An all-MLP Architecture for Vision
- Embedding Watermarks into Deep Neural Networks
- Recent progress in semantic image segmentation
- Adversarial Frontier Stitching for Remote Neural Network Watermarking
- Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
- CycleMLP: A MLP-like Architecture for Dense Prediction
- DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models
- P3: Toward Privacy-Preserving Photo Sharing
- Adversarial Machine Learning -- Industry Perspectives
- Privacy-Preserving Support Vector Machine Computing Using Random Unitary Transformation
- A Privacy-Preserving Machine Learning Scheme Using EtC Images
- A Reversible Data Hiding Method in Compressible Encrypted Images
- Block shuffling learning for Deepfake Detection