AMR Steganalysis Based on Second-Order Difference of Pitch Delay

This paper presents a novel steganalysis scheme for the detection of adaptive multi-rate (AMR) audio steganography. AMR audio codec is used widely in mobile communication and mobile Internet system. Due to the modifiability of pitch delay, several AMR steganography schemes based on pitch delay modulation have emerged gradually and have high capacity and good imperceptibility. Based on the difference between cover and stego AMR audios on the continuity of adjacent pitch delay, this paper proposes the matrix of the second-order difference of pitch delay (MSDPD) steganalysis features by calculating the Markov transition probability MSDPD, and uses the calibration method to estimate the cover's features to get the calibrated MSDPD features to improve the accuracy of the scheme. Support vector machine is used as the steganalyzer to test the performance of our proposed scheme. The experimental results show that the correct detection rate of our proposed method is more than 85% when the embedding bit rate is 30% or above, and can reach above 85% for cover audios. The results of contrast experiment show that the performance of our proposed method is better than the existing method, especially on low embedding rate. The method can be extended to other CELP codec, such as G.723.1 and G.729.