Steganalysis on character substitution using support vector machine

Zhao Xinxin; Huang Liusheng; Li Lingjun; Yang Wei; Chen Zhili; Yu Zhenshan

doi:10.1109/WKDD.2009.105

Steganalysis on character substitution using support vector machine

Zhao Xinxin^*
, Huang Liusheng
, Li Lingjun
, Yang Wei
, Chen Zhili
, Yu Zhenshan

^*Corresponding author for this work

University of Science and Technology of China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

A new steganalysis method is proposed to detect the exists of hidden information using character substitution in texts. This is done by utilizing Support Vector Machine (SVM) as a classifier to classify the characteristic vector input into SVM. The most important step of this detection algorithm is the construction of a proper characteristic vector. Under the prerequisite that the secret bits to be embedded are uniformly distributed, the distribution of the characters used for hiding data has altered after steganographic process, thus the ratio of abnormal characters to normal characters is different in cover texts and stego texts. Experimental results demonstrate that this method can reliably detect whether there is hidden information in texts. The detection accuracy in experiment reaches as high as 96% while the embedding data rate is merely 20%.

Original language	English
Title of host publication	2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009
Pages	84-88
Number of pages	5
DOIs	https://doi.org/10.1109/WKDD.2009.105
State	Published - 2009
Externally published	Yes
Event	2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009 - Moscow, Russian Federation Duration: 23 Jan 2009 → 25 Jan 2009

Publication series

Name	Proceedings - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009

Conference

Conference	2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009
Country/Territory	Russian Federation
City	Moscow
Period	23/01/09 → 25/01/09

Keywords

Character substitution
Characteristic vector
SVM
Steganalysis

Access to Document

10.1109/WKDD.2009.105

Cite this

Xinxin, Z., Liusheng, H., Lingjun, L., Wei, Y., Zhili, C., & Zhenshan, Y. (2009). Steganalysis on character substitution using support vector machine. In 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009 (pp. 84-88). Article 4771884 (Proceedings - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009). https://doi.org/10.1109/WKDD.2009.105

@inproceedings{592d04990ea547868bf114b1dbf674d8,

title = "Steganalysis on character substitution using support vector machine",

abstract = "A new steganalysis method is proposed to detect the exists of hidden information using character substitution in texts. This is done by utilizing Support Vector Machine (SVM) as a classifier to classify the characteristic vector input into SVM. The most important step of this detection algorithm is the construction of a proper characteristic vector. Under the prerequisite that the secret bits to be embedded are uniformly distributed, the distribution of the characters used for hiding data has altered after steganographic process, thus the ratio of abnormal characters to normal characters is different in cover texts and stego texts. Experimental results demonstrate that this method can reliably detect whether there is hidden information in texts. The detection accuracy in experiment reaches as high as 96\% while the embedding data rate is merely 20\%.",

keywords = "Character substitution, Characteristic vector, SVM, Steganalysis",

author = "Zhao Xinxin and Huang Liusheng and Li Lingjun and Yang Wei and Chen Zhili and Yu Zhenshan",

year = "2009",

doi = "10.1109/WKDD.2009.105",

language = "英语",

isbn = "9780769535432",

series = "Proceedings - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009",

pages = "84--88",

booktitle = "2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009",

note = "2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009 ; Conference date: 23-01-2009 Through 25-01-2009",

}

Xinxin, Z, Liusheng, H, Lingjun, L, Wei, Y, Zhili, C & Zhenshan, Y 2009, Steganalysis on character substitution using support vector machine. in 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009., 4771884, Proceedings - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009, pp. 84-88, 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009, Moscow, Russian Federation, 23/01/09. https://doi.org/10.1109/WKDD.2009.105

Steganalysis on character substitution using support vector machine. / Xinxin, Zhao; Liusheng, Huang; Lingjun, Li et al.
2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009. 2009. p. 84-88 4771884 (Proceedings - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Steganalysis on character substitution using support vector machine

AU - Xinxin, Zhao

AU - Liusheng, Huang

AU - Lingjun, Li

AU - Wei, Yang

AU - Zhili, Chen

AU - Zhenshan, Yu

PY - 2009

Y1 - 2009

N2 - A new steganalysis method is proposed to detect the exists of hidden information using character substitution in texts. This is done by utilizing Support Vector Machine (SVM) as a classifier to classify the characteristic vector input into SVM. The most important step of this detection algorithm is the construction of a proper characteristic vector. Under the prerequisite that the secret bits to be embedded are uniformly distributed, the distribution of the characters used for hiding data has altered after steganographic process, thus the ratio of abnormal characters to normal characters is different in cover texts and stego texts. Experimental results demonstrate that this method can reliably detect whether there is hidden information in texts. The detection accuracy in experiment reaches as high as 96% while the embedding data rate is merely 20%.

AB - A new steganalysis method is proposed to detect the exists of hidden information using character substitution in texts. This is done by utilizing Support Vector Machine (SVM) as a classifier to classify the characteristic vector input into SVM. The most important step of this detection algorithm is the construction of a proper characteristic vector. Under the prerequisite that the secret bits to be embedded are uniformly distributed, the distribution of the characters used for hiding data has altered after steganographic process, thus the ratio of abnormal characters to normal characters is different in cover texts and stego texts. Experimental results demonstrate that this method can reliably detect whether there is hidden information in texts. The detection accuracy in experiment reaches as high as 96% while the embedding data rate is merely 20%.

KW - Character substitution

KW - Characteristic vector

KW - SVM

KW - Steganalysis

UR - https://www.scopus.com/pages/publications/66249139877

U2 - 10.1109/WKDD.2009.105

DO - 10.1109/WKDD.2009.105

M3 - 会议稿件

AN - SCOPUS:66249139877

SN - 9780769535432

T3 - Proceedings - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009

SP - 84

EP - 88

BT - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009

T2 - 2009 2nd International Workshop on Knowledge Discovery and Data Mining, WKKD 2009

Y2 - 23 January 2009 through 25 January 2009

ER -

Steganalysis on character substitution using support vector machine

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this