Steganalisis pada media audio menggunakan metode Support Vector Machine Radial Basis jiICntion (SVM-Rbf) Classifier

Abstract

We address the problem of detecting the presence of hidden messages in audio. The detector is based on the characteristics of the denoised residuals of the audio, which may consist of a mixture of speech and music data. A set of generalized moments of the audio signal is measured in terms of objective and perceptual quality measures. The detector discriminates between cover and stego files using a selected subset of features and an Support Vector Machine (SYM) classifier. The proposed scheme achieves on the average 82,5 % discrimination perfomance on individual stegnographic tools. The perfomance for detecting non-embedded hidden messages in audio data is 25 % discrimination. Generally 63,3 % discrimination perfomance is achieved in universal tests. Experimental results show that the proposed tec1mique can be used to detect the presence of hidden messages in digital audio data.