Image Universal Steganalysis Based on Wavelet Packet Transform

To improve the correct detection ratio of existing universal detection methods for image steganography, a new universal steganalysis method based on wavelet package transform (WPT) is presented. Firstly, decompose image into three scales through WPT to obtain 85 coefficient subbands together, and extract the multi-order absolute characteristic function moments of histogram from them as features. And then, normalize these features and combine them to a 255-D feature vector for each image. Lastly, according to this vector, a back-propagation (BP) neural network is designed to classify cover and stego images. A series of experiments validate the performance of proposed method for four kinds of typical steganography of BMP and JPEG images, such as LSB, SS (Spread spectrum), Jsteg and F5 steganography methods. Results show that the proposed method can detect the stego and original images reliably, and the average detection accuracy of our method exceeds those of its closest competitors by at least 7.7% and up to 16.5%.