This paper concentrates on the detection of steganography in inactive frames of low bit\nrate audio streams in Voice over Internet Protocol (VoIP) scenarios. Both theoretical and experimental\nanalyses demonstrate that the distribution of 0 and 1 in encoding parameter bits becomes symmetric\nafter a steganographic process. Moreover, this symmetry affects the frequency of each subsequence\nof parameter bits, and accordingly changes the poker test statistical features of encoding parameter\nbits. Employing the poker test statistics of each type of encoding parameter bits as detection features,\nwe present a steganalysis method based on a support vector machine. We evaluate the proposed\nmethod with a large quantity of speech samples encoded by G.723.1 and compare it with the entropy\ntest. The experimental results show that the proposed method is effective, and largely outperforms\nthe entropy test in any cases.
Loading....