Share Email Print

Proceedings Paper

JPEG quantization table mismatched steganalysis via robust discriminative feature transformation
Author(s): Likai Zeng; Xiangwei Kong; Ming Li; Yanqing Guo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The cover source mismatch is a common problem in steganalysis, which may result in the degradation of detection accuracy. In this paper, we present a novel method to mitigate the problem of JPEG quantization table mismatch, named as Robust Discriminative Feature Transformation (RDFT). RDFT transforms original features to new feature representations based on a non-linear transformation matrix. It can improve the statistical consistency of the training samples and testing samples and learn new matched feature representations from original features by minimizing feature distribution difference while preserving the classification ability of training data. The comparison to prior arts reveals that the detection accuracy of the proposed RDFT algorithm can significantly outperform traditional steganalyzers under mismatched conditions and it is close to that of matched scenario. RDFT has several appealing advantages: 1) it can improve the statistical consistency of the training and testing data; 2) it can reduce the distribution difference between the training features and testing features; 3) it can preserve the classification ability of the training data; 4) it is robust to parameters and can achieve a good performance under a wide range of parameter values.

Paper Details

Date Published: 4 March 2015
PDF: 9 pages
Proc. SPIE 9409, Media Watermarking, Security, and Forensics 2015, 94090U (4 March 2015); doi: 10.1117/12.2078188
Show Author Affiliations
Likai Zeng, Dalian Univ. of Technology (China)
Xiangwei Kong, Dalian Univ. of Technology (China)
Ming Li, Dalian Univ. of Technology (China)
Yanqing Guo, Dalian Univ. of Technology (China)
State Information Ctr. (China)

Published in SPIE Proceedings Vol. 9409:
Media Watermarking, Security, and Forensics 2015
Adnan M. Alattar; Nasir D. Memon; Chad D. Heitzenrater, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?