Steganography can be used to hide information in audio me-
dia both for the purposes of digital watermarking and stablishing covert communication channels. Digital audio provides a suitable cover for high-throughput steganography as a result of its transient and unpredictable characteristics. Distortion measure plays an important role in audio ste-
ganalysis - the analysis and classi¯cation method of determining if an audio medium is carrying hidden information. In this paper, we propose a novel distortion metric based on Hausdor® distance. Given an audio
object x which could potentially be a stego-audio object, we consider its de-noised version x0 as an estimate of the cover-object. We then use Hausdor® distance to measure the distortion from x to x0. The distortion measurement is obtained at various wavelet decomposition levels
from which we derive high-order statistics as features for a classier to determine the presence of hidden information in an audio signal. Extensive experimental results for the Least Signicant Bit (LSB) substitution based steganography tool show that the proposed algorithm has a strong
discriminatory ability and the performance is signi¯cantly superior to existing methods. The proposed approach can be easily applied to other steganography tools and algorithms.
