JPEG圖像失配隱密分析研究
發(fā)布時(shí)間：2019-01-27 07:34
【摘要】：隨著網(wǎng)絡(luò)通信技術(shù)的發(fā)展,以隱蔽通信為目的的隱密術(shù)受到了社會(huì)的廣泛關(guān)注。隱密術(shù)是指將秘密信息嵌入到載體數(shù)據(jù)的冗余位置,利用公開信道以不被察覺的方式進(jìn)行秘密通信的技術(shù)。雖然隱密術(shù)在隱密通信和知識(shí)產(chǎn)權(quán)保護(hù)等方面給社會(huì)提供了便利,但也被不法分子應(yīng)用到隱蔽地傳輸消息等方面,給社會(huì)的安全帶來了嚴(yán)重的威脅。因此,研究如何從公共信道的海量數(shù)據(jù)中識(shí)別出含有秘密信息的文件的隱密分析技術(shù)具有重要的現(xiàn)實(shí)意義。 傳統(tǒng)隱密分析依賴于已經(jīng)獲得隱密者的載體樣本和含密樣本的假設(shè)。而在實(shí)際應(yīng)用中,該假設(shè)通常不會(huì)滿足,使得隱密分析會(huì)出現(xiàn)失配問題。目前,雖然已經(jīng)有許多文獻(xiàn)指出失配問題會(huì)導(dǎo)致傳統(tǒng)隱密分析算法性能下降,但鮮有有效的算法能夠克服隱密分析中的失配問題。本文從機(jī)器學(xué)習(xí)角度出發(fā),研究了失配因素對(duì)于傳統(tǒng)隱密分析特征的影響,針對(duì)不同的應(yīng)用環(huán)境,提出了基于局部領(lǐng)域泛化的融合訓(xùn)練失配隱密分析以及基于遷移學(xué)習(xí)的失配隱密分析廣義轉(zhuǎn)移成分分析方法。本文的研究成果如下： (1)首先介紹了傳統(tǒng)隱密分析框架,包括研究背景和意義、基本概念和研究現(xiàn)狀,重點(diǎn)介紹了幾種典型的隱密分析特征和常用的機(jī)器學(xué)習(xí)工具。其次,給出失配隱密分析框架,分別從載體圖像生成過程和含密圖像生成過程討論了不同的失配因素對(duì)于傳統(tǒng)隱密分析性能的影響。最后,總結(jié)了前人失配隱密分析的研究方法,分析了各個(gè)方法的應(yīng)用環(huán)境和優(yōu)缺點(diǎn)。 (2)通過總結(jié)前人基于融合訓(xùn)練失配隱密分析的策略,提出基于局部領(lǐng)域泛化的融合訓(xùn)練方法。該方法引入待測(cè)圖像局部領(lǐng)域的概念,通過降低待測(cè)圖像局部領(lǐng)域特征分布的方差,并且保持局部領(lǐng)域訓(xùn)練數(shù)據(jù)和標(biāo)簽的相關(guān)性,提取能夠泛化局部領(lǐng)域的公有特征,利用該特征對(duì)待測(cè)圖像進(jìn)行隱密分析。將該融合訓(xùn)練方法與前人融合訓(xùn)練方法進(jìn)行比較,在相同的實(shí)驗(yàn)環(huán)境下,失配隱密分析的判決錯(cuò)誤率降低了2%-6%。 (3)針對(duì)基于融合訓(xùn)練失配隱密分析方法訓(xùn)練數(shù)據(jù)的多樣性需求的局限性,引入遷移學(xué)習(xí)的思想,提出廣義轉(zhuǎn)移成分分析失配隱密分析方法。此方法可以根據(jù)不同的測(cè)試圖像,自適應(yīng)的調(diào)整單源的訓(xùn)練庫數(shù)據(jù)的特征分布,使得其能應(yīng)用于多種失配因素的隱密分析檢測(cè)。通過與前人方法的比較,該方法能夠在有限的單源的訓(xùn)練數(shù)據(jù)的情況下,使得其達(dá)到與融合訓(xùn)練同等級(jí)的失配隱密分析的性能。此外,該方法對(duì)于多種失配因素具有魯棒性。
[Abstract]:With the development of network communication technology, covert communication has been paid more and more attention. Steganography refers to the technology of embedding secret information into the redundant position of carrier data and using open channels to communicate secretly in an undetected manner. Although secret technology provides convenience to society in secret communication and intellectual property protection, it is also used by lawless elements to transmit information in secret, which brings serious threat to the security of society. Therefore, it is of great practical significance to study how to identify the secret analysis technology of files containing secret information from the mass data of common channels. Traditional cryptographic analysis relies on the assumption that carrier samples and secret samples have been obtained. However, in practical application, the assumption is usually not satisfied, which leads to the mismatch problem. At present, although many literatures have pointed out that the mismatch problem will lead to the performance degradation of the traditional secret analysis algorithm, there are few effective algorithms to overcome the mismatch problem in the secret analysis. From the point of view of machine learning, this paper studies the influence of mismatch factors on the characteristics of traditional secret analysis, aiming at different application environments. In this paper, a fusion training mismatch secret analysis based on local domain generalization and a generalized transfer component analysis method based on transfer learning are proposed. The results of this paper are as follows: (1) this paper firstly introduces the traditional secret analysis framework, including the research background and significance, basic concepts and research status, focusing on the introduction of several typical features of secret analysis and commonly used machine learning tools. Secondly, the mismatch secret analysis framework is given, and the influence of different mismatch factors on the performance of traditional secret analysis is discussed from the process of image generation and the process of generating secret image respectively. Finally, the research methods of mismatch secret analysis are summarized, and the application environment, advantages and disadvantages of each method are analyzed. (2) by summing up the previous strategy of mismatch secret analysis based on fusion training, a fusion training method based on local domain generalization is proposed. This method introduces the concept of the local domain of the image under test. By reducing the variance of the local domain feature distribution of the image under test, and keeping the correlation between the local domain training data and the label, the public features of the local domain can be generalized. The feature is used for secret analysis of the measured image. The fusion training method is compared with the previous fusion training method. Under the same experimental environment, the error rate of mismatch secret analysis is reduced by 2%-6%. (3) aiming at the limitation of diversity requirement of training data based on fusion training mismatch secret analysis method, a generalized transfer component analysis mismatch secret analysis method is proposed by introducing the idea of transfer learning. This method can adaptively adjust the feature distribution of single source training database data according to different test images, so that it can be applied to the hidden analysis and detection of many mismatch factors. Compared with previous methods, this method can achieve the performance of mismatch secret analysis with the same level of fusion training under the condition of limited single source training data. In addition, the method is robust to various mismatch factors.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP309.7
本文編號(hào)：2416051
[Abstract]:With the development of network communication technology, covert communication has been paid more and more attention. Steganography refers to the technology of embedding secret information into the redundant position of carrier data and using open channels to communicate secretly in an undetected manner. Although secret technology provides convenience to society in secret communication and intellectual property protection, it is also used by lawless elements to transmit information in secret, which brings serious threat to the security of society. Therefore, it is of great practical significance to study how to identify the secret analysis technology of files containing secret information from the mass data of common channels. Traditional cryptographic analysis relies on the assumption that carrier samples and secret samples have been obtained. However, in practical application, the assumption is usually not satisfied, which leads to the mismatch problem. At present, although many literatures have pointed out that the mismatch problem will lead to the performance degradation of the traditional secret analysis algorithm, there are few effective algorithms to overcome the mismatch problem in the secret analysis. From the point of view of machine learning, this paper studies the influence of mismatch factors on the characteristics of traditional secret analysis, aiming at different application environments. In this paper, a fusion training mismatch secret analysis based on local domain generalization and a generalized transfer component analysis method based on transfer learning are proposed. The results of this paper are as follows: (1) this paper firstly introduces the traditional secret analysis framework, including the research background and significance, basic concepts and research status, focusing on the introduction of several typical features of secret analysis and commonly used machine learning tools. Secondly, the mismatch secret analysis framework is given, and the influence of different mismatch factors on the performance of traditional secret analysis is discussed from the process of image generation and the process of generating secret image respectively. Finally, the research methods of mismatch secret analysis are summarized, and the application environment, advantages and disadvantages of each method are analyzed. (2) by summing up the previous strategy of mismatch secret analysis based on fusion training, a fusion training method based on local domain generalization is proposed. This method introduces the concept of the local domain of the image under test. By reducing the variance of the local domain feature distribution of the image under test, and keeping the correlation between the local domain training data and the label, the public features of the local domain can be generalized. The feature is used for secret analysis of the measured image. The fusion training method is compared with the previous fusion training method. Under the same experimental environment, the error rate of mismatch secret analysis is reduced by 2%-6%. (3) aiming at the limitation of diversity requirement of training data based on fusion training mismatch secret analysis method, a generalized transfer component analysis mismatch secret analysis method is proposed by introducing the idea of transfer learning. This method can adaptively adjust the feature distribution of single source training database data according to different test images, so that it can be applied to the hidden analysis and detection of many mismatch factors. Compared with previous methods, this method can achieve the performance of mismatch secret analysis with the same level of fusion training under the condition of limited single source training data. In addition, the method is robust to various mismatch factors.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：TP309.7
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 黃煒;趙險(xiǎn)峰;盛任農(nóng);;基于KFD指標(biāo)聚類的高隱蔽性JPEG隱寫分析[J];計(jì)算機(jī)學(xué)報(bào);2012年09期
相關(guān)博士學(xué)位論文 前1條
1 郭艷卿;隱密對(duì)抗的理論及方法研究[D];大連理工大學(xué);2009年
，本文編號(hào)：2416051
本文鏈接：http://sikaile.net/falvlunwen/zhishichanquanfa/2416051.html
最近更新
教材專著
