Image Classification Using Vision Transformer for EtC Images

Hamano, Genki; Imaizumi, Shoko; Kiya, Hitoshi

doi:10.23919/apsipaasc55919.2022.9980144

Cited by 2 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We give an overview of ViT [ 21 ] and summarize our previous method [ 17 ] in this section. We previously proposed an image classification method using ViT with novel advantages; copyrights for both a trained ViT model and test images can be protected simultaneously without any decrease in the accuracy of classification, and the test images are effectively compressed using lossless image compression standards.…”

Section: Preparationmentioning

confidence: 99%

“…Another approach for protecting copyright and privacy information in test images is to conceal the visual information. Image encryption is a typical technique for concealing visual information, and image-encryption methods have been actively studied to train encrypted images using deep neural networks [ 3 , 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 ]. The method in [ 3 ] combines federated learning with image encryption for test images.…”

Section: Introductionmentioning

confidence: 99%

“…As an extension of the method [ 16 ], we previously introduced an EtC system for the image encryption process [ 17 ]. The EtC system is based on a block-wise transformation, and thus the EtC images can maintain high compression performance.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, we not only successfully avoid any degradation to the classification accuracy but also compress the encrypted images. In [ 17 ], we surveyed the performance of lossless compression using JPEG-LS [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

“…On the basis of our previous method [ 17 ], this paper, for the first time, investigates the effects of JPEG compression, which is a widely used lossy compression standard, on the classification accuracy. In our experiments, we confirm that a high classification accuracy can be preserved even for JPEG-compressed EtC images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Effects of JPEG Compression on Vision Transformer Image Classification for Encryption-then-Compression Images

Hamano

Imaizumi

Kiya

2023

Sensors

Self Cite

View full text Add to dashboard Cite

This paper evaluates the effects of JPEG compression on image classification using the Vision Transformer (ViT). In recent years, many studies have been carried out to classify images in the encrypted domain for privacy preservation. Previously, the authors proposed an image classification method that encrypts both a trained ViT model and test images. Here, an encryption-then-compression system was employed to encrypt the test images, and the ViT model was preliminarily trained by plain images. The classification accuracy in the previous method was exactly equal to that without any encryption for the trained ViT model and test images. However, even though the encrypted test images can be compressible, the practical effects of JPEG, which is a typical lossy compression method, have not been investigated so far. In this paper, we extend our previous method by compressing the encrypted test images with JPEG and verify the classification accuracy for the compressed encrypted-images. Through our experiments, we confirm that the amount of data in the encrypted images can be significantly reduced by JPEG compression, while the classification accuracy of the compressed encrypted-images is highly preserved. For example, when the quality factor is set to 85, this paper shows that the classification accuracy can be maintained at over 98% with a more than 90% reduction in the amount of image data. Additionally, the effectiveness of JPEG compression is demonstrated through comparison with linear quantization. To the best of our knowledge, this is the first study to classify JPEG-compressed encrypted images without sacrificing high accuracy. Through our study, we have come to the conclusion that we can classify compressed encrypted-images without degradation to accuracy.

show abstract

Section: Preparationmentioning

confidence: 99%