Title :
Detection of Synonym-Substitution Modified Articles Using Context Information
Author :
Yu, Zhenshan ; Huang, Liusheng ; Chen, Zhili ; Li, Lingjun ; Zhao, Xinxin ; Zhu, Youwen
Author_Institution :
Dept. of Comput. Sci. & Technol., Univ. of Sci. & Technol. of China, Hefei, China
Abstract :
Text steganography usually modifies the cover-text (where secrets are embedded) in some meaning-preserving ways to conceal secret messages, while steganalysis does the opposite - detects or extracts the secrets. A lot of work has been done on steganography, but only a little on steganalysis. In this paper, we analyze one kind of text steganography that use synonym substitution. We try to distinguish between modified articles and unmodified articles using context information. We evaluate the suitability of words for their context, and then the suitability sequence of words leads to the final judgment made by a SVM (support vector machine) classifier. IDF (inverse document frequency) is used to weight words¿ suitability in order to balance common words and rare ones. This scheme is evaluated on internet instead of in a specific corpus, with the help of Google. Experimental results show that classification accuracy achieves 90.0%.
Keywords :
Internet; pattern classification; steganography; support vector machines; text analysis; Google; Internet; classification accuracy; context information; cover-text; inverse document frequency; secret messages; steganalysis; suitability sequence; support vector machine classifier; synonym substitution; synonym-substitution modified articles; text steganography; Algorithm design and analysis; Context; Humans; Internet; Nominations and elections; Robustness; Steganography; Support vector machine classification; Support vector machines; Voting;
Conference_Titel :
Future Generation Communication and Networking, 2008. FGCN '08. Second International Conference on
Conference_Location :
Hainan Island
Print_ISBN :
978-0-7695-3431-2
DOI :
10.1109/FGCN.2008.39