Presentation | 2020-02-27 An Image Transformation Network for Privacy-Preserving Deep Neural Networks Hiroki Ito, Yuma Kinoshita, Hitoshi Kiya, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose an image transformation network to generate visually-protected images for privacy-preserving deep neural networks (DNNs). The transformation network inspired by adversarial examples is considered not only to generate visually-protected images but also to achieve the performance of DNNs that using plain images has. Moreover, the proposed transformation network can be public to users, so there is no need to manage secret keys. In an image classification experiment, the proposed transformation network is confirmed to protect the visual information without any performance degradation under the use of two image classification networks: ResNet and VGG. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Adversarial example / deep neural network / privacy preserving / visual protection |
Paper # | ITS2019-37,IE2019-75 |
Date of Issue | 2020-02-20 (ITS, IE) |
Conference Information | |
Committee | ITE-HI / IE / ITS / ITE-MMS / ITE-ME / ITE-AIT |
---|---|
Conference Date | 2020/2/27(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Hokkaido Univ. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Image Processing, etc. |
Chair | Takehiro Nagai(Tokyo Inst. of Tech.) / / / Norihiko Ishii(NHK) / Norio Tagawa(Tokyo Metropolitan Univ.) / Nobuhiko Mukai(Tokyo Cisy Univ.) |
Vice Chair | / / / / Hiroyuki Arai(Nippon Institute of Technology) / Hisaki Nate(Tokyo Polytechnic Univ.) |
Secretary | (NTT) / / / (Fukuoka Univ.) / Hiroyuki Arai(NHK) / Hisaki Nate(NHK) |
Assistant |
Paper Information | |
Registration To | Technical Group on Human Inormation / Technical Committee on Image Engineering / Technical Committee on Intelligent Transport Systems Technology / Technical Group on Multi-media Storage / Technical Group on Media Engineering / Technical Group on Artistic Image Technology |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An Image Transformation Network for Privacy-Preserving Deep Neural Networks |
Sub Title (in English) | |
Keyword(1) | Adversarial example |
Keyword(2) | deep neural network |
Keyword(3) | privacy preserving |
Keyword(4) | visual protection |
1st Author's Name | Hiroki Ito |
1st Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
2nd Author's Name | Yuma Kinoshita |
2nd Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
3rd Author's Name | Hitoshi Kiya |
3rd Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
Date | 2020-02-27 |
Paper # | ITS2019-37,IE2019-75 |
Volume (vol) | vol.119 |
Number (no) | ITS-421,IE-422 |
Page | pp.pp.195-200(ITS), pp.195-200(IE), |
#Pages | 6 |
Date of Issue | 2020-02-20 (ITS, IE) |