Performance Evaluation of Steganography Tools Using SVM and NPR Tool

Author

Bansal, Dipali ; Chhikara, Rita

Author_Institution

Dept. of Comput. Sci. & Eng., ITM Univ., Gurgaon, India

fYear

2014

fDate

8-9 Feb. 2014

Firstpage

483

Lastpage

487

Abstract

Steganography is the art of hiding the secret messages in an innocent medium like images, audio, video, text, etc. such that the existence of any secret message is not revealed. There are various Steganography tools available. In this paper, we are considering three algorithms - nsF5, PQ,Outguess. To compare the robustness and to withstand the steganalytic attack of the above three algorithms, an algorithm based on sensitive features is presented. SVM and Neural Network Pattern Recognition Tool is used on sensitive features extracted from DCT domain. A comparison between the accuracy obtained from SVM and NPR is also shown. Experimental results show that the Outguess method can withstand steganalytic attack by a margin of 35% accuracy as compared to nsF5 and PQ, hence Outguess is more reliable for Steganography.

Keywords

data compression; discrete cosine transforms; feature extraction; image coding; neural nets; performance evaluation; steganography; support vector machines; DCT domain; JPEG feature set; NPR tool; Outguess algorithm; PQ algorithm; SVM tool; discrete cosine transform; neural network pattern recognition tool; nsF5 algorithm; performance evaluation; secret message hiding; sensitive feature extraction; steganalytic attack; steganography tools; support vector machine; Accuracy; Discrete cosine transforms; Feature extraction; Histograms; Pattern recognition; Support vector machines; Training; Discrete Cosine Transform; Neural Network Pattern Recognition; Outguess; PQ; SVM; Steganography; nsF5;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Computing & Communication Technologies (ACCT), 2014 Fourth International Conference on

Conference_Location

Rohtak

Type

conf

DOI

10.1109/ACCT.2014.17

Filename

6783501