基于模糊C均值聚类与单类支持向量机的音频隐写分析方法

Audio steganalysis method based on fuzzy C-means clustering and one class support vector machine

针对传统的二分类音频隐写分析方法对未知隐写方法的适应性较差的问题,提出了一种基于模糊C均值(FCM)聚类与单类支持向量机(OC-SVM)的音频隐写分析方法。在训练过程中,首先对训练音频进行特征提取,包括短时傅里叶变换(STFT)频谱的统计特征和基于音频质量测度的特征,然后对所提取的特征进行FCM聚类得到C个聚类,最后送入多个超球面的OC-SVM分类器进行训练;检测过程中,对测试音频进行特征提取,根据多个超球面OC-SVM分类器的边界对待测音频进行检测。实验结果表明,该隐写分析方法对于几种典型的音频隐写方法能够较为正确地检测,满容量嵌入时,测试音频的总体检测率达到85.1%,与K-means聚类方法相比,所提方法的检测正确率提高了至少2%。该隐写分析方法比二分类的隐写分析方法更具有通用性,更适用于隐写方法事先未知情况下的隐写音频的检测。

Concerning the poor adaptability of the traditional audio steganalysis method using two-class classifier to the unknown steganography method,an audio steganalysis method based on Fuzzy C-Means（ FCM） clustering and One Class Support Vector Machine（ OC-SVM） was proposed. In the process of training,features were extracted from the training audio firstly,including the statistical features of the spectrum of the Short-Time Fourier Transform（ STFT）,and the features based on audio quality measures; and then FCM clustering was executed on the extracted features to obtain C clusters; finally the extracted features were trained by the OC-SVM classifier with multiple hyperspheres. In the process of detecting,the features were extracted from the testing audio,and the testing audio was detected according to the boundary of the OC-SVM with multiple hyperspheres. The experimental results reveal that,for some typical methods of audio steganography,this steganalysis method can detect accurately,when the embedding capacity is full,the total detection accuracy is 85. 1%; furthermore,compared with the method of K-means clustering,this method can improve the detection accuracy by at least 2%. This steganalysis method is more universal than the steganalysis method using two-class classifier,and it is more suitable for the detection of the stego-audio whose steganography method is unknown beforehand.