Image Generation Method Based on the Recoverable Byte Sequence using the Neural Networks

I. V. Rudakov, M. V. Filippov, M. A. Kudryavtsev
{"title":"Image Generation Method Based on the Recoverable Byte Sequence using the Neural Networks","authors":"I. V. Rudakov, M. V. Filippov, M. A. Kudryavtsev","doi":"10.18698/0236-3933-2023-1-83-97","DOIUrl":null,"url":null,"abstract":"Due to the rapid development of information technologies, the tasks of ensuring information integrity, safety and confidentiality, as well as the possibility of guaranteed confirmation of its source, are becoming more relevant than ever. One of the possible solutions to this problem could be the steganographic methods, which allow both hiding the fact of information transfer and imperceptibly adding the useful data. Scientific literature describes a large number of steganographic algorithms. However, only insignificant number of works is devoted to the data hiding methods using the neural networks, and even less are devoted to generating containers for them. A method for generating images based on the hidden information is proposed, which guarantees possibility of both hiding and subsequent extraction of information eliminating the need to select an appropriate container. As part of the method, an algorithm was developed that included description of the stages of input data preprocessing, transformation into the container image and extraction of the hidden information. Examples of the proposed method operation are provided. The method could serve both as a steganographic algorithm for hiding information and as the algorithm for adding information in the form of watermarks","PeriodicalId":12961,"journal":{"name":"Herald of the Bauman Moscow State Technical University. Series Natural Sciences","volume":"13 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Herald of the Bauman Moscow State Technical University. Series Natural Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18698/0236-3933-2023-1-83-97","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 0

Abstract

Due to the rapid development of information technologies, the tasks of ensuring information integrity, safety and confidentiality, as well as the possibility of guaranteed confirmation of its source, are becoming more relevant than ever. One of the possible solutions to this problem could be the steganographic methods, which allow both hiding the fact of information transfer and imperceptibly adding the useful data. Scientific literature describes a large number of steganographic algorithms. However, only insignificant number of works is devoted to the data hiding methods using the neural networks, and even less are devoted to generating containers for them. A method for generating images based on the hidden information is proposed, which guarantees possibility of both hiding and subsequent extraction of information eliminating the need to select an appropriate container. As part of the method, an algorithm was developed that included description of the stages of input data preprocessing, transformation into the container image and extraction of the hidden information. Examples of the proposed method operation are provided. The method could serve both as a steganographic algorithm for hiding information and as the algorithm for adding information in the form of watermarks
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于可恢复字节序列的神经网络图像生成方法
由于信息技术的迅速发展,确保信息的完整性、安全性和保密性以及保证确认其来源的可能性的任务变得比以往任何时候都更加重要。这个问题的一个可能的解决方案是隐写方法,它既可以隐藏信息传输的事实,又可以在不知不觉中添加有用的数据。科学文献描述了大量的隐写算法。然而,研究神经网络数据隐藏方法的文献并不多,研究神经网络容器生成的文献就更少了。提出了一种基于隐藏信息生成图像的方法,保证了信息的隐藏和后续提取的可能性,省去了选择合适容器的需要。作为该方法的一部分,开发了一种算法,该算法包括输入数据预处理、转换到容器图像和提取隐藏信息的阶段描述。给出了所提方法操作的实例。该方法既可以作为隐藏信息的隐写算法,也可以作为以水印形式添加信息的算法
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
1.10
自引率
0.00%
发文量
40
期刊介绍: The journal is aimed at publishing most significant results of fundamental and applied studies and developments performed at research and industrial institutions in the following trends (ASJC code): 2600 Mathematics 2200 Engineering 3100 Physics and Astronomy 1600 Chemistry 1700 Computer Science.
期刊最新文献
Semi-Classical Quantum Generalization of the London Equations and the Monopole Hypothesis Investigation of the PAH and Carbon Nanoparticles Formation Processes in the Ethylene Pyrolysis with the Tetrahydrofuran Addition Behind the Shock Waves Gas-Dynamic Stabilization and Intensification of the Methane Oxidation Macrokinetic Processes in the High-Enthalpy Oxygen-Containing Flow Saint-Venant Principle on Problems of Nonlocal Elasticity Theory Acenaphthene Nitro Derivatives Plasma-Chemical Synthesis in the High-Frequency Currents Field at Reduced Pressure
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1