Presentation | 2019-01-17 An Access Control Mechanism for Pre-trained ML Models in Mobile Apps Atsuya Sato, Katsuya Matsubara, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Utilizing machine learning inference on mobile platforms has been made real since recent smartphones may have high-performance processors and hardware accelerators of signal and image processing. However, the machine learning inference on the current mobile platform could bring issues. One of the most significant issues is that any machine learning inferences can be unlimitedly applied to personal data which once the application got permitted to. Furthermore, it could be quite hard to understand afterward the behavior of a 'learned' machine learning model and the behavior of an installed application can be transparently modified by replacing a used model. This research aims to implement an access control against such functionalities of machine learning inference for mobile platforms. In this paper, we describe how to identified learned models and how to implement permission control at Android Neural Networks API for Android as a target platform. And we also show an evaluation result with a prototype implementation. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Machine learning inference / Android / Smartphone / Access control |
Paper # | MoNA2018-69 |
Date of Issue | 2019-01-09 (MoNA) |
Conference Information | |
Committee | MoNA |
---|---|
Conference Date | 2019/1/16(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | T. B. D. |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Ryoichi Shinkuma(Kyoto Univ.) |
Vice Chair | Shigeaki Tagashira(Kansai Univ.) / Gen Kitagata(Tohoku Univ.) |
Secretary | Shigeaki Tagashira(Kyushu Univ.) / Gen Kitagata(NEC) |
Assistant | Ken Usui(KDDI Research) / Kenji Kanai(Waseda Univ.) |
Paper Information | |
Registration To | Technical Committee on Mobile Network and Applications |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An Access Control Mechanism for Pre-trained ML Models in Mobile Apps |
Sub Title (in English) | |
Keyword(1) | Machine learning inference |
Keyword(2) | Android |
Keyword(3) | Smartphone |
Keyword(4) | Access control |
1st Author's Name | Atsuya Sato |
1st Author's Affiliation | Future University Hakodate(Future Univ. Hakodate) |
2nd Author's Name | Katsuya Matsubara |
2nd Author's Affiliation | Future University Hakodate(Future Univ. Hakodate) |
Date | 2019-01-17 |
Paper # | MoNA2018-69 |
Volume (vol) | vol.118 |
Number (no) | MoNA-389 |
Page | pp.pp.69-74(MoNA), |
#Pages | 6 |
Date of Issue | 2019-01-09 (MoNA) |