Audio steganalysis of DSSS based on audio distortion measures
Lin Li · Journal of the Graduate School of the Chinese Academy of Sciences · 2008
Given the observation under repeated embedding,the audio distortion is the fiercest for the very first time and drops significantly subsequently,a steganalysis method of DSSS(Direct Sequence Spread Spectrum)was proposed,which is implemented by support vector machine(SVM)as a classifier,using various distortion measures sensitive to DSSS stego-method as features,avoiding estimation of the original signal.The experiment results verify that the proposed method can detect the DSSS embedding effectively and can also work with different embedding strength,and two methods of detection with different embedding capacities were suggested.