基于水印的深度学习模型所有权保护

IF 4 3区 计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE
Md. Ishfaque Ahmed , Kedar Nath Singh , Himanshu Kumar Singh , Amit Kumar Singh , Amrit Kumar Agrawal
{"title":"基于水印的深度学习模型所有权保护","authors":"Md. Ishfaque Ahmed ,&nbsp;Kedar Nath Singh ,&nbsp;Himanshu Kumar Singh ,&nbsp;Amit Kumar Singh ,&nbsp;Amrit Kumar Agrawal","doi":"10.1016/j.compeleceng.2025.110481","DOIUrl":null,"url":null,"abstract":"<div><div>Deep learning (DL) models have achieved remarkable success in the multimedia domain. However, the potential misuse of these powerful models poses significant challenges in many security-sensitive domains. To address this issue, digital watermarking schemes have emerged, aiming to embed watermark information into DL models to prove copyright ownership. In this paper, we propose a copyright protection scheme for DL models to resolve ownership conflicts and enhance overall system security. Initially, we generate two different watermarks using chaotic and Gold sequences. The generated watermarks are then embedded into selected layers of the DL model using redundant discrete wavelet transform and singular value decomposition. After the watermarking process, we shuffle the model’s weights before sharing it with a third party. On the receiver’s side, the inverse of the embedding process, followed by watermark verification, ensures secure access to authentic and unaltered model data. Ownership analysis shows that the proposed scheme is robust against pruning and fine-tuning attacks. Experimental results further validate the effectiveness of the proposed scheme compared to other competitive approaches.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"125 ","pages":"Article 110481"},"PeriodicalIF":4.0000,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Ownership protection of deep learning models using watermarking\",\"authors\":\"Md. Ishfaque Ahmed ,&nbsp;Kedar Nath Singh ,&nbsp;Himanshu Kumar Singh ,&nbsp;Amit Kumar Singh ,&nbsp;Amrit Kumar Agrawal\",\"doi\":\"10.1016/j.compeleceng.2025.110481\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Deep learning (DL) models have achieved remarkable success in the multimedia domain. However, the potential misuse of these powerful models poses significant challenges in many security-sensitive domains. To address this issue, digital watermarking schemes have emerged, aiming to embed watermark information into DL models to prove copyright ownership. In this paper, we propose a copyright protection scheme for DL models to resolve ownership conflicts and enhance overall system security. Initially, we generate two different watermarks using chaotic and Gold sequences. The generated watermarks are then embedded into selected layers of the DL model using redundant discrete wavelet transform and singular value decomposition. After the watermarking process, we shuffle the model’s weights before sharing it with a third party. On the receiver’s side, the inverse of the embedding process, followed by watermark verification, ensures secure access to authentic and unaltered model data. Ownership analysis shows that the proposed scheme is robust against pruning and fine-tuning attacks. Experimental results further validate the effectiveness of the proposed scheme compared to other competitive approaches.</div></div>\",\"PeriodicalId\":50630,\"journal\":{\"name\":\"Computers & Electrical Engineering\",\"volume\":\"125 \",\"pages\":\"Article 110481\"},\"PeriodicalIF\":4.0000,\"publicationDate\":\"2025-06-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers & Electrical Engineering\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0045790625004240\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Electrical Engineering","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0045790625004240","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0

摘要

深度学习(DL)模型在多媒体领域取得了显著的成功。然而,这些强大模型的潜在误用在许多安全敏感领域带来了重大挑战。为了解决这个问题,出现了数字水印方案,旨在将水印信息嵌入到深度学习模型中以证明版权所有权。在本文中,我们提出了一种DL模型的版权保护方案,以解决所有权冲突并提高整个系统的安全性。首先,我们使用混沌序列和黄金序列生成两种不同的水印。然后使用冗余离散小波变换和奇异值分解将生成的水印嵌入到DL模型的选定层中。在水印过程之后,我们在与第三方共享之前对模型的权重进行洗牌。在接收方,嵌入过程的逆过程,以及随后的水印验证,确保了对真实和未改变的模型数据的安全访问。所有权分析表明,该方案对剪枝和微调攻击具有鲁棒性。实验结果进一步验证了该方法的有效性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Ownership protection of deep learning models using watermarking
Deep learning (DL) models have achieved remarkable success in the multimedia domain. However, the potential misuse of these powerful models poses significant challenges in many security-sensitive domains. To address this issue, digital watermarking schemes have emerged, aiming to embed watermark information into DL models to prove copyright ownership. In this paper, we propose a copyright protection scheme for DL models to resolve ownership conflicts and enhance overall system security. Initially, we generate two different watermarks using chaotic and Gold sequences. The generated watermarks are then embedded into selected layers of the DL model using redundant discrete wavelet transform and singular value decomposition. After the watermarking process, we shuffle the model’s weights before sharing it with a third party. On the receiver’s side, the inverse of the embedding process, followed by watermark verification, ensures secure access to authentic and unaltered model data. Ownership analysis shows that the proposed scheme is robust against pruning and fine-tuning attacks. Experimental results further validate the effectiveness of the proposed scheme compared to other competitive approaches.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Computers & Electrical Engineering
Computers & Electrical Engineering 工程技术-工程:电子与电气
CiteScore
9.20
自引率
7.00%
发文量
661
审稿时长
47 days
期刊介绍: The impact of computers has nowhere been more revolutionary than in electrical engineering. The design, analysis, and operation of electrical and electronic systems are now dominated by computers, a transformation that has been motivated by the natural ease of interface between computers and electrical systems, and the promise of spectacular improvements in speed and efficiency. Published since 1973, Computers & Electrical Engineering provides rapid publication of topical research into the integration of computer technology and computational techniques with electrical and electronic systems. The journal publishes papers featuring novel implementations of computers and computational techniques in areas like signal and image processing, high-performance computing, parallel processing, and communications. Special attention will be paid to papers describing innovative architectures, algorithms, and software tools.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信