PROCEEDINGS OF THE ITE ANNUAL CONVENTION
Online ISSN : 2424-2292
Print ISSN : 1343-1846
ISSN-L : 1343-1846
Proceedings of the ITE Annual Convention 2018
Conference information

Requirements Analysis on Watermarks in a Deep Learning Model
*Shigeyuki Sakazawa
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Pages 22B-4-

Details
Abstract
Watermarking for deep learning models is discussed. Firstly, it is noted that the value of the trained deep learning model. Then, watermark technologies as copyright protection are reviewed including latest research activities. Furthermore, evaluation items of the deep learning watermarks are summarized with consideration on malicious attacks.
Content from these authors
© 2018 The Institute of Image Information and Television Engineers
Previous article Next article
feedback
Top