Copyright protection of deep neural network models using digital watermarking: a comparative study

Author:

Fkirin AlaaORCID,Attiya GamalORCID,El-Sayed AymanORCID,Shouman Marwa A.ORCID

Abstract

AbstractNowadays, deep learning achieves higher levels of accuracy than ever before. This evolution makes deep learning crucial for applications that care for safety, like self-driving cars and helps consumers to meet most of their expectations. Further, Deep Neural Networks (DNNs) are powerful approaches that employed to solve several issues. These issues include healthcare, advertising, marketing, computer vision, speech processing, natural language processing. The DNNs have marvelous progress in these different fields, but training such DNN models requires a lot of time, a vast amount of data and in most cases a lot of computational steps. Selling such pre-trained models is a profitable business model. But, sharing them without the owner permission is a serious threat. Unfortunately, once the models are sold, they can be easily copied and redistributed. This paper first presents a review of how digital watermarking technologies are really very helpful in the copyright protection of the DNNs. Then, a comparative study between the latest techniques is presented. Also, several optimizers are proposed to improve the accuracy against the fine-tuning attack. Finally, several experiments are performed with black-box settings using several optimizers and the results are compared with the SGD optimizer.

Funder

Fayoum University

Publisher

Springer Science and Business Media LLC

Subject

Computer Networks and Communications,Hardware and Architecture,Media Technology,Software

Reference66 articles.

1. Abadi M, Barham P, Chen J et al (2016) TensorFlow : a system for large-scale machine learning this paper is included in the proceedings of the TensorFlow : a system for large-scale machine learning. In: Proceedings of the 12th USENIX conference on operating systems design and implementation, pp 265–283

2. Adi Y, Baum C, Cisse M et al (2018) Turning your weakness into a strength : watermarking deep neural networks by Backdooring. In: Proceedings of the 27th USENIX security symposium, pp 1615–1631

3. Ali M, Ahn CW, Pant M (2014) A robust image watermarking technique using SVD and differential evolution in DCT domain. International Journal for Light and Electron Optics 125:428–434. https://doi.org/10.1016/j.ijleo.2013.06.082

4. AL-Mansoori S, Kunhu A (2012) Robust watermarking technique based on DCT to protect the ownership of DubaiSat-1 images against attacks. International Journal of Computer Science and Network Security (IJCSNS) 12:1–9

5. Bordes A, Weston J, Chopra S (2014) Question answering with subgraph Embeddings. In: Proceedings of Empirical Methods in Natural Language Processing, pp 1–10

Cited by 24 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3