TY - GEN
T1 - Detection of synonym-substitution modified articles using context information
AU - Yu, Zhenshan
AU - Huang, Liusheng
AU - Chen, Zhili
AU - Li, Lingjun
AU - Zhao, Xinxin
AU - Zhu, Youwen
PY - 2008
Y1 - 2008
N2 - 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%.
AB - 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%.
UR - https://www.scopus.com/pages/publications/62349104082
U2 - 10.1109/FGCN.2008.39
DO - 10.1109/FGCN.2008.39
M3 - 会议稿件
AN - SCOPUS:62349104082
SN - 9780769534312
T3 - Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008
SP - 134
EP - 139
BT - Proceedings of the 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008
T2 - 2008 2nd International Conference on Future Generation Communication and Networking, FGCN 2008
Y2 - 13 December 2008 through 15 December 2008
ER -