Audio steganalysis of spread spectrum hiding based on statistical moment

Audio information hiding has attracted more attentions recently. Spread spectrum (SS) technique has developed rapidly in this area due to the advantages of good robustness and immunity to noise attack. Accordingly steganalysis of the SS hiding effectively verify the presence of the secrete message in an important issue. In this paper we present two algorithms for steganalysis SS hiding. Both the two methods based on machine learning theory and discrete wavelet transform (DWT). In the algorithm I, we introduce Gaussian mixture model (GMM) and generalize Gaussian distribution (GGD) to character the probability distribution of wavelet sub-band. Then the absolute probability distribution function (PDF) moment is extracted as feature vectors. In the algorithm II, we propose distance metric between GMM and GGD of wavelet sub-band to distinguish cover and stego audio. Four distances (Kullback-Leibler Distance, Bhattacharyya Distance, Earth Mover´s Distance, L2 Distance) are calculated as feature vectors. The support vector machine (SVM) classifier is utilized for classification. The experiment results of both two proposed algorithms may obtain better detecting performance. Its simplicity and extensibility indicate further application in other audio steganalysis.