Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images
The need for cloud servers for training deep neural network (DNN) models is increasing as more complex architecture designs of DNN models are developed. Nevertheless, cloud servers are considered semi-honest. With great attention to the privacy issues of medical diagnoses using a DNN, previous studi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9802995/ |
| _version_ | 1811332795632451584 |
|---|---|
| author | Qi-Xian Huang Wai Leong Yap Min-Yi Chiu Hung-Min Sun |
| author_facet | Qi-Xian Huang Wai Leong Yap Min-Yi Chiu Hung-Min Sun |
| author_sort | Qi-Xian Huang |
| collection | DOAJ |
| description | The need for cloud servers for training deep neural network (DNN) models is increasing as more complex architecture designs of DNN models are developed. Nevertheless, cloud servers are considered semi-honest. With great attention to the privacy issues of medical diagnoses using a DNN, previous studies have proposed the idea of learnable image encryption. Though some methods have been presented to partially attack previous encryption schemes, there is still some space for improvement. We proposed a learnable image encryption scheme that is an enhanced version of previous methods and can be used to train a great DNN model and simultaneously keep the privacy of training images. We conducted an experiment on medical datasets from open sources and the result demonstrates the effectiveness of our proposed method in performance and privacy-preserving. |
| first_indexed | 2024-04-13T16:42:19Z |
| format | Article |
| id | doaj.art-f6bf4d7fede744eea562baaf383cc1fb |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-13T16:42:19Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f6bf4d7fede744eea562baaf383cc1fb2022-12-22T02:39:12ZengIEEEIEEE Access2169-35362022-01-0110663456635510.1109/ACCESS.2022.31852069802995Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical ImagesQi-Xian Huang0Wai Leong Yap1Min-Yi Chiu2Hung-Min Sun3https://orcid.org/0000-0003-0870-9973Institute of Information Systems and Applications, National Tsing Hua University, Hsinchu, TaiwanInstitute of Information Systems and Applications, National Tsing Hua University, Hsinchu, TaiwanInstitute of Information Systems and Applications, National Tsing Hua University, Hsinchu, TaiwanDepartment of Computer Science, National Tsing Hua University, Hsinchu, TaiwanThe need for cloud servers for training deep neural network (DNN) models is increasing as more complex architecture designs of DNN models are developed. Nevertheless, cloud servers are considered semi-honest. With great attention to the privacy issues of medical diagnoses using a DNN, previous studies have proposed the idea of learnable image encryption. Though some methods have been presented to partially attack previous encryption schemes, there is still some space for improvement. We proposed a learnable image encryption scheme that is an enhanced version of previous methods and can be used to train a great DNN model and simultaneously keep the privacy of training images. We conducted an experiment on medical datasets from open sources and the result demonstrates the effectiveness of our proposed method in performance and privacy-preserving.https://ieeexplore.ieee.org/document/9802995/Deep neural networklearnable image encryptionmedical analysisprivacy-preserving |
| spellingShingle | Qi-Xian Huang Wai Leong Yap Min-Yi Chiu Hung-Min Sun Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images IEEE Access Deep neural network learnable image encryption medical analysis privacy-preserving |
| title | Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images |
| title_full | Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images |
| title_fullStr | Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images |
| title_full_unstemmed | Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images |
| title_short | Privacy-Preserving Deep Learning With Learnable Image Encryption on Medical Images |
| title_sort | privacy preserving deep learning with learnable image encryption on medical images |
| topic | Deep neural network learnable image encryption medical analysis privacy-preserving |
| url | https://ieeexplore.ieee.org/document/9802995/ |
| work_keys_str_mv | AT qixianhuang privacypreservingdeeplearningwithlearnableimageencryptiononmedicalimages AT waileongyap privacypreservingdeeplearningwithlearnableimageencryptiononmedicalimages AT minyichiu privacypreservingdeeplearningwithlearnableimageencryptiononmedicalimages AT hungminsun privacypreservingdeeplearningwithlearnableimageencryptiononmedicalimages |