Image and Model Transformation with Secret Key for Vision Transformer

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,...

Full description

Saved in:
Bibliographic Details
Published inIEICE Transactions on Information and Systems Vol. E106.D; no. 1; pp. 2 - 11
Main Authors MAUNGMAUNG, Aprilpyone, IIJIMA, Ryota, KIYA, Hitoshi, KINOSHITA, Yuma
Format Journal Article
LanguageEnglish
Published Tokyo The Institute of Electronics, Information and Communication Engineers 01.01.2023
Japan Science and Technology Agency
Subjects
DNN
Image classification
perceptual image encryption
Performance degradation
privacy preserving
Transformers
vision transformer
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0916-8532
1745-1361
DOI:10.1587/transinf.2022MUI0001