Attacks on Digital Watermarks for Deep Neural Networks

Training deep neural networks is a computationally expensive task. Furthermore, models are often derived from proprietary datasets that have been carefully prepared and labelled. Hence, creators of deep learning models want to protect their models against intellectual property theft. However, this i...

Full description

Bibliographic Details

Published in:	ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 2622 - 2626
Main Authors:	Wang, Tianhao, Kerschbaum, Florian
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-05-2019
Subjects:	At-tack Computational modeling Deep Neural Network Detection algorithms Mathematical model Neural networks Training Watermark Watermarking
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!