Presentation 2018-11-05
[Poster Presentation] Watermarking of Neural Network with Exponential Weighting Parameters
Ryota Namba, Jun Sakuma,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, neural network models need to be treated as valuable intellectual properties. One concern in such a situation is that some malicious user might redistribute the model or provide a prediction service using the model without permission. One promising solution is digital watermarking, to embed a mechanism into the model so that the owner of the model can verify the ownership of the model externally. In this study, we present a novel watermarking method that is tolerant of both model modification and query modification. We experimentally show that our watermarking method achieves high verification performance even under a malicious attempt of unauthorized model users such as model modification and query modification.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) machine learning / deep learning / digital watermarking
Paper # IBISML2018-63
Date of Issue 2018-10-29 (IBISML)

Conference Information
Committee IBISML
Conference Date 2018/11/5(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Hokkaido Citizens Activites Center (Kaderu 2.7)
Topics (in Japanese) (See Japanese page)
Topics (in English) Information-Based Induction Science Workshop (IBIS2018)
Chair Hisashi Kashima(Kyoto Univ.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST)
Assistant Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] Watermarking of Neural Network with Exponential Weighting Parameters
Sub Title (in English)
Keyword(1) machine learning
Keyword(2) deep learning
Keyword(3) digital watermarking
1st Author's Name Ryota Namba
1st Author's Affiliation University of Tsukuba(Tsukuba Univ.)
2nd Author's Name Jun Sakuma
2nd Author's Affiliation University of Tsukuba/riken AIP(Tsukuba Univ./riken)
Date 2018-11-05
Paper # IBISML2018-63
Volume (vol) vol.118
Number (no) IBISML-284
Page pp.pp.143-150(IBISML),
#Pages 8
Date of Issue 2018-10-29 (IBISML)