Stego-Breaker: Defeating the Steganographic Systems through Genetic-X-Means approach using Image Quality Metrics

Steganography is used to hide the occurrence of communication. This creates a potential problem when this technology is misused for planning criminal activities. Differentiating anomalous images (stego image) from pure images (cover image) is difficult and tedious. This paper investigates the use of a Genetic-X-means classifier, which distinguishes a pure image from the adulterated one. The basic idea is that, the various Image Quality Metrics (IQMs) calculated on cover images and on stego-images vis-a-vis their denoised versions, are statistically different. Our model employs these IQMs to steganalyse the image data. Genetic paradigm is exploited to select the IQMs that are sensitive to various embedding techniques. The classifier between cover and stego-files is built using X-means clustering on the selected feature set. The presented method can not only detect the presence of hidden message but also identify the hiding domains. The experimental results show that the combination strategy (Genetic-X-means) can improve the classification precision even with lesser payload compared to the traditional ANN (Back Propagation Network).