| Presentation | 2020-10-01 Evaluation of linear dimensionality reduction methods considering visual information protection for privacy-preserving machine learning Masaki Kitayama, Nobutaka Ono, Hitoshi Kiya, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, linear dimensionality reduction methods are evaluated in terms of difficulty in estimating the visual information of original images from dimensionally reduced ones. Dimensionality reduction in machine learning has been widely used to avoid negative effects that high-dimensional data have on machine learning models. In recent years, dimensionality reduction methods are also used for protecting the visual information of images for privacy-preserving machine learning. In this paper, we apply typical linear dimensionality reduction methods to image data, and experimentally evaluate their robustness against various possible visual information estimation attacks. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | dimensionality reduction / machine learning / privacy-preserving |
| Paper # | SIS2020-13 |
| Date of Issue | 2020-09-24 (SIS) |
| Conference Information | |
| Committee | SIS / ITE-BCT |
|---|---|
| Conference Date | 2020/10/1(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | System Implementation Technology, Short Range Wireless Systems, Smart Multimedia Systems, Broadcasting Technology, etc. |
| Chair | Noriaki Suetake(Yamaguchi Univ.) / Kyoichi Saito(NHK) |
| Vice Chair | Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.) |
| Secretary | Tomoaki Kimura(Kindai Univ.) / Naoto Sasaoka(National Inst. of Tech., Ube College) / (NHK) |
| Assistant | Yukihiro Bandoh(NTT) / Soh Yoshida(Kansai Univ.) / Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Shoichiro Sekiguchi(NHK) / Toshiharu Morizumi(NTT) / Toshimitsu Kobayashi(NBN) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems / Technical Group on Broadcasting and Communication Technologies |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Evaluation of linear dimensionality reduction methods considering visual information protection for privacy-preserving machine learning |
| Sub Title (in English) | |
| Keyword(1) | dimensionality reduction |
| Keyword(2) | machine learning |
| Keyword(3) | privacy-preserving |
| 1st Author's Name | Masaki Kitayama |
| 1st Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
| 2nd Author's Name | Nobutaka Ono |
| 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 | 2020-10-01 |
| Paper # | SIS2020-13 |
| Volume (vol) | vol.120 |
| Number (no) | SIS-176 |
| Page | pp.pp.17-22(SIS), |
| #Pages | 6 |
| Date of Issue | 2020-09-24 (SIS) |