{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T00:15:26Z","timestamp":1770423326395,"version":"3.49.0"},"reference-count":38,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:00:00Z","timestamp":1731283200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS KAKENHI","award":["JP21H01327"],"award-info":[{"award-number":["JP21H01327"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>We propose an enhanced privacy-preserving method for image classification using ConvMixer, which is an extremely simple model that is similar in spirit to the Vision Transformer (ViT). Most privacy-preserving methods using encrypted images cause the performance of models to degrade due to the influence of encryption, but a state-of-the-art method was demonstrated to have the same classification accuracy as that of models without any encryption under the use of ViT. However, the method, in which a common secret key is assigned to each patch, is not robust enough against ciphertext-only attacks (COAs) including jigsaw puzzle solver attacks if compressible encrypted images are used. In addition, ConvMixer is less robust than ViT because there is no position embedding. To overcome this issue, we propose a novel block-wise encryption method that allows us to assign an independent key to each patch to enhance robustness against attacks. In experiments, the effectiveness of the method is verified in terms of image classification accuracy and robustness, and it is compared with conventional privacy-preserving methods using image encryption.<\/jats:p>","DOI":"10.3390\/info15110723","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T06:28:32Z","timestamp":1731392912000},"page":"723","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Privacy-Preserving ConvMixer Without Any Accuracy Degradation Using Compressible Encrypted Images"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0758-7510","authenticated-orcid":false,"given":"Haiwei","family":"Lin","sequence":"first","affiliation":[{"name":"Graduate School of Science and Engineering, Chiba University, Chiba 263-8522, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6515-9109","authenticated-orcid":false,"given":"Shoko","family":"Imaizumi","sequence":"additional","affiliation":[{"name":"Graduate School of Informatics, Chiba University, Chiba 263-8522, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8061-3090","authenticated-orcid":false,"given":"Hitoshi","family":"Kiya","sequence":"additional","affiliation":[{"name":"Faculty of System Design, Tokyo Metropolitan University, Tokyo 191-0065, Japan"}]}],"member":"1968","published-online":{"date-parts":[[2024,11,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e11","DOI":"10.1561\/116.00000048","article-title":"An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications","volume":"11","author":"Kiya","year":"2022","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, H., and Yang, Z. (2024, January 19\u201323). Enforcing End-to-End Security for Remote Conference Applications. Proceedings of the 45th IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP54263.2024.00236"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"34296","DOI":"10.1109\/JIOT.2024.3437452","article-title":"Privacy-Preserving Resource Management for Distributed Collaborative Edge Caching Systems","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yuge, N., Ishihara, H., Nakamura, M., and Nakachi, T. (2024). Privacy Preserving Deep Unrolling Methods and Its Application to Image Reconstruction. IEICE Trans. Fundam. Electron. Commun. Comput. Sci.","DOI":"10.1587\/transfun.2024SMP0006"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Shimizu, K., and Suzuki, T. (2020, January 4\u20138). Flexibly-Tunable Bitcube-Based Perceptual Encryption within Jpeg Compression. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.","DOI":"10.1109\/ICASSP40776.2020.9053759"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hinojosa, C., Marquez, M., Arguello, H., Adeli, E., Fei-Fei, L., and Niebles, J.C. (2022, January 23\u201327). PrivHAR: Recognizing Human Actions From Privacy-Preserving Lens. Proceedings of the European Conference on Computer Vision (ECCV), Tel Aviv, Israel.","DOI":"10.1007\/978-3-031-19772-7_19"},{"key":"ref_7","unstructured":"Bhaskar, M. (2019). Cryptographic and Information Security Approaches for Images and Videos, CRC Press. [1st ed.]. Cryptographic Image Scrambling Techniques."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"109236","DOI":"10.1016\/j.compeleceng.2024.109236","article-title":"Deep Learning-Based Encryption for Secure Transmission Digital Images: A Survey","volume":"116","author":"Rohhila","year":"2024","journal-title":"Comput. Electr. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Perez, F., Lopez, J., and Arguello, H. (2024, January 14\u201319). Privacy-Preserving Deep Learning Using Deformable Operators for Secure Task Learning. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.","DOI":"10.1109\/ICASSP48485.2024.10446218"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sirichotedumrong, W., Chuman, T., Imaizumi, S., and Kiya, H. (2018, January 23\u201327). Grayscale-Based Block Scrambling Image Encryption for Social Networking Services. Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), San Diego, CA, USA.","DOI":"10.1109\/ICME.2018.8486525"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ahmad, I., Choi, W., and Shin, S. (2023). Comprehensive Analysis of Compressible Perceptual Encryption Methods\u2014Compression and Encryption Perspectives. Sensors, 23.","DOI":"10.3390\/s23084057"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Tanaka, M. (2018, January 19\u201321). Learnable Image Encryption. Proceedings of the IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), Taichung, Taiwan.","DOI":"10.1109\/ICCE-China.2018.8448772"},{"key":"ref_13","unstructured":"Madono, K., Tanaka, M., Onishi, M., and Ogawa, T. (2020, January 7\u201312). Block-Wise Scrambled Image Recognition Using Adaptation Network. Proceedings of the Workshop on AAAI Conference Artificial Intelligence, New York, NY, USA."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1109\/MMUL.2022.3168441","article-title":"Privacy-Preserving Image Classification Using an Isotropic Network","volume":"29","author":"AprilPyone","year":"2022","journal-title":"IEEE Multimed."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1333","DOI":"10.1109\/TIFS.2017.2787987","article-title":"Privacy-Preserving Deep Learning via Additively Homomorphic Encryption","volume":"13","author":"Phong","year":"2018","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4289","DOI":"10.1109\/JIOT.2023.3302065","article-title":"Secure Federated Learning With Fully Homomorphic Encryption for IoT Communications","volume":"11","author":"Hijazi","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"30039","DOI":"10.1109\/ACCESS.2022.3159694","article-title":"Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network","volume":"10","author":"Lee","year":"2022","journal-title":"IEEE Access"},{"key":"ref_18","first-page":"1330","article-title":"Towards the AlexNet Moment for Homomorphic Encryption: HCNN, the First Homomorphic CNN on Encrypted Data With GPUs","volume":"9","author":"Jin","year":"2020","journal-title":"IEEE Trans. Emerging Top. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1109\/TNSE.2023.3285070","article-title":"A Novel Homomorphic Encryption and Consortium Blockchain-Based Hybrid Deep Learning Model for Industrial Internet of Medical Things","volume":"10","author":"Ali","year":"2023","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106854","DOI":"10.1016\/j.cie.2020.106854","article-title":"A Review of Applications in Federated Learning","volume":"149","author":"Li","year":"2020","journal-title":"Comput. Ind. Eng."},{"key":"ref_21","unstructured":"Kone\u010dn\u00fd, J., McMahan, H.B., Yu, F.X., Richt\u00e1rik, P., Suresh, A.T., and Bacon, D. (2016). Federated Learning: Strategies for Improving Communication Efficiency. arXiv."},{"key":"ref_22","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1587\/transinf.2022MUI0001","article-title":"Image and Model Transformation with Secret Key for Vision Transformer","volume":"E106","author":"Kiya","year":"2023","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chuman, T., and Kiya, H. (2023). A Jigsaw Puzzle Solver-Based Attack on Image Encryption Using Vision Transformer for Privacy-Preserving DNNs. Information, 14.","DOI":"10.3390\/info14060311"},{"key":"ref_25","unstructured":"Trockman, A., and Kolter, J.Z. (2022). Patches are all you need?. arXiv."},{"key":"ref_26","unstructured":"Krizhevsky, A. (2009). Learning Multiple Layers of Features from Tiny Images. [Master\u2019s Thesis, Department of Computer Science, University of Toronto]. Available online: https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ishikawa, Y., Kondo, M., and Kataoka, H. (2024, January 4\u20138). Learnable Cube-Based Video Encryption for Privacy-Preserving Action Recognition. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV57701.2024.00685"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Dave, I.R., Chen, C., and Shah, M. (2022, January 18\u201324). SPAct: Self-Supervised Privacy Preservation for Action Recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01953"},{"key":"ref_29","unstructured":"Hao, F., He, F., Wang, Y., Wu, F., Cheng, J., and Tao, D. (2024, October 04). Privacy-Preserving Vision Transformer on Permutation-Encrypted Images. Available online: https:\/\/openreview.net\/forum?id=eL1iX7DMnPI."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"69206","DOI":"10.1109\/ACCESS.2024.3400958","article-title":"A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense","volume":"12","author":"Iijima","year":"2024","journal-title":"IEEE Access"},{"key":"ref_31","first-page":"e10","article-title":"A protection method of trained CNN model with a secret key from unauthorized access","volume":"10","author":"AprilPyone","year":"2021","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"177844","DOI":"10.1109\/ACCESS.2019.2959017","article-title":"Pixel-Based Image Encryption Without Key Management for Privacy-Preserving Deep Neural Networks","volume":"7","author":"Sirichotedumrong","year":"2019","journal-title":"IEEE Access"},{"key":"ref_33","unstructured":"Chang, A.H., and Case, B.M. (2020). Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"64629","DOI":"10.1109\/ACCESS.2021.3074968","article-title":"Image to Perturbation: An Image Transformation Network for Generating Visually Protected Images for Privacy-Preserving Deep Neural Networks","volume":"9","author":"Ito","year":"2021","journal-title":"IEEE Access"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Baidya, R., and Jeong, H. (2022). YOLOv5 with ConvMixer Prediction Heads for Precise Object Detection in Drone Imagery. Sensors, 22.","DOI":"10.3390\/s22218424"},{"key":"ref_36","unstructured":"Ross, W. (2024, September 23). Pytorch Image Models. Available online: https:\/\/github.com\/huggingface\/pytorch-image-models."},{"key":"ref_37","unstructured":"(2024, September 23). Independent JPEG Group. Available online: https:\/\/www.ijg.org."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Li, F.-F. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/11\/723\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:30:02Z","timestamp":1760113802000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/11\/723"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,11]]},"references-count":38,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["info15110723"],"URL":"https:\/\/doi.org\/10.3390\/info15110723","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,11]]}}}