Steganalysis on echo hiding based on combinatorial high order statistics

Authors:
Wang Yunlu;Ye Xueyi;Zhao Zemao
Affiliations:
Hangzhou Dianzi University, Hangzhou, Zhejiang;Hangzhou Dianzi University, Hangzhou, Zhejiang;Hangzhou Dianzi University, Hangzhou, Zhejiang
Venue:
Proceedings of the First International Conference on Internet Multimedia Computing and Service
Year:
2009

Citing 5
Cited 0

Techniques for data hiding

IBM Systems Journal
Chaotic-Type Features for Speech Steganalysis

IEEE Transactions on Information Forensics and Security
Steganalysis using image quality metrics

IEEE Transactions on Image Processing
Optimal Signature Design for Spread-Spectrum Steganography

IEEE Transactions on Image Processing
A novel echo-hiding scheme with backward and forward kernels

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we describe an effective steganalysis for four kinds of echo hiding based on combinatorial high order statistics. We analyze effect on power cepstrum, due to statistic characteristic changing with echo in stego speech. High order statistics of each segment of power cepstrum firstly are calculated, including coefficients of skewness and kurtosis. Then we compute high order statistics of segmented skewness and kurtosis in combination. The combinatorial high order statistics of original speech and echoed speech are trained with SVM. By obtaining combinatorial high order statistics thresholds, we can used them for blind steganalysis of echo hiding. Experimental results are compared and show that our proposed steganalysis with three combinatorial high order statistics performs well in detecting Ker.1, Ker.3 and Ker.4 echo hiding, and skewness-kurtosis achieves high detecting correct rate in four kinds of echo hiding.