基于二元依存同义词替换隐写算法  

Two-gram dependency synonym substitution-based steganographic algorithm

作　　者：霍林[1] 肖豫川 Huo Lin;Xiao Yuchuan(School of Computer&Electric Information,Guangxi University,Nanning 530004,China)

机构地区：[1]广西大学计算机与电子信息学院,南宁530004

出　　处：《计算机应用研究》2018年第4期1174-1178,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61262072);广西工业和信息化委员会信息服务项目发展基金资助项目(201333)

摘　　要：针对在自然语言文本信息隐写术中,采用基于同义词替换方法来嵌入秘密信息时,常由于候选同义词选择不准确导致替换后文本语句出现明显错误或逻辑歧义等问题,提出了基于二元依存同义词替换隐写算法。该算法首先从Word Net词库中得出与目标词词性相同、语义相似的词语,然后对目标语句利用依存句法提取同义词对应的二元依存关系,从大规模语料库中计算二元依存关系的向量距离,得出最佳替换的同义词词集。实验结果表明,该算法生成的隐写文本保持嵌入秘密信息后文本特征属性不变,比目前改进的同义词替换算法更能保证文本语法正确、语义完整,更高效地抵抗同义词结对和相对词频统计分析检测,提高了秘密信息传递的安全性。In linguistic steganography,when the text using synonym substitution-base method embeds secret information,obvious mistakes and logical misconceptions,resulted from the inaccuracy of candidate synonyms,are ubiquitous.In order to solve this problem,this paper proposed a new steganography algorithm based on two-gram dependency synonym substitution.Firstly,this algorithm chose the synonym which had the same attribute and semantic as the target word from the WordNet sets.Secondly,it extracted the two-gram dependency relation of synonym from the target sentence using dependency syntactic,and obtained the best synonym substitution set by calculating vector distance of two-gram dependency relation in a large-scale corpus.Experimental results show that the stego text generated by using this algorithm keeps the same property of the text after embedding secret information.In comparison to the current advanced synonym substitution,it not only can better ensure the accuracy of grammar and completeness of semantics,but can resist attacks made by detection algorithms using statistical features based on the synonyms pairing and relative frequency more efficiently,guarantees the security of secret information.

关 键 词：文本 信息隐藏 同义词 二元依存词语 向量距离 

分 类 号：TP309.2[自动化与计算机技术—计算机系统结构]