Steganalysis of least significant bit matching using multi-order differences

ABSTRACT This paper presents a learning‐based steganalysis/detection method to attack spatial domain least significant bit (LSB) matching steganography in grayscale images, which is the antetype of many sophisticated steganographic methods. We model the message embedded by LSB matching as the independent noise to the image, and theoretically prove that LSB matching smoothes the histogram of multi‐order differences. Because of the dependency among neighboring pixels, histogram of low order differences can be approximated by Laplace distribution. The smoothness caused by LSB matching is especially apparent at the peak of the histogram. Consequently, the low order differences of image pixels are calculated. The co‐occurrence matrix is utilized to model the differences with the small absolute value in order to extract features. Finally, support vector machine classifiers are trained with the features so as to identify a test image either an original or a stego image. The proposed method is evaluated by LSB matching and its improved version “Hugo”. In addition, the proposed method is compared with state‐of‐the‐art steganalytic methods. The experimental results demonstrate the reliability of the new detector. Copyright © 2013 John Wiley & Sons, Ltd. A learning‐based steganalysis method is proposed in this paper. In the training process, feature vectors are extracted from original image set and stego image set with a certain “feature extraction” method. The images are represented by these feature vectors. Then the extracted feature vectors are used to train a “classifier” with a certain classification algorithm such as support vector machine. In the testing process, we first extract the feature vector with the same extraction method from the testing image. Then the classifier is used to judge whether the feature vector is extracted from a stego image or not. Feature extraction is key for learning‐based steganalysis. In this paper, we calculate multi‐order differences horizontally and vertically. Then co‐occurrence matrix is used to model the difference to extract features.