保护预训练 DNN 模型所有权的混合两级保护系统

Alaa Fkirin, Ahmed Samy Moursi, Gamal Attiya, Ayman El-Sayed, Marwa A. Shouman
{"title":"保护预训练 DNN 模型所有权的混合两级保护系统","authors":"Alaa Fkirin, Ahmed Samy Moursi, Gamal Attiya, Ayman El-Sayed, Marwa A. Shouman","doi":"10.1007/s00521-024-10304-0","DOIUrl":null,"url":null,"abstract":"<p>Recent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods.</p>","PeriodicalId":18925,"journal":{"name":"Neural Computing and Applications","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Hybrid two-level protection system for preserving pre-trained DNN models ownership\",\"authors\":\"Alaa Fkirin, Ahmed Samy Moursi, Gamal Attiya, Ayman El-Sayed, Marwa A. Shouman\",\"doi\":\"10.1007/s00521-024-10304-0\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Recent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods.</p>\",\"PeriodicalId\":18925,\"journal\":{\"name\":\"Neural Computing and Applications\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neural Computing and Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1007/s00521-024-10304-0\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Computing and Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1007/s00521-024-10304-0","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

深度神经网络(DNN)的最新进展使其在众多商业应用中变得不可或缺。这些应用包括医疗保健系统和自动驾驶汽车。训练 DNN 模型通常需要大量时间、庞大的数据集和高昂的计算成本。然而,这些宝贵的模型也面临着巨大的风险。攻击者可以窃取并出售预训练的 DNN 模型以牟利。未经授权共享这些模型构成了严重威胁。这些模型一旦售出,就很容易被复制和重新分发。因此,精心构建的预训练 DNN 模型是需要保护的宝贵资产。本文介绍了一种稳健的两级混合保护系统,用于保护预训练 DNN 模型的所有权。第一级采用零位水印。第二级通过使用扰动技术嵌入水印,将对抗性攻击作为水印。针对七种类型的攻击,对拟议系统的鲁棒性进行了评估。这些攻击包括快速梯度法攻击、自动投影梯度下降攻击、自动共轭梯度攻击、基本迭代法攻击、动量迭代法攻击、正方形攻击和自动攻击。所提出的两级保护系统可抵御所有七种攻击类型。它保持了准确性,并超越了当前最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Hybrid two-level protection system for preserving pre-trained DNN models ownership

Hybrid two-level protection system for preserving pre-trained DNN models ownership

Recent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods.

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
自引率
0.00%
发文量
0
×
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:481959085
Book学术官方微信