Feature based classification system for JPEG steganalysis

Abstract

The objective of steganalysis is to detect messages hidden in cover images, such as digital images. The ultimate goal of a steganalyst is to extract and decipher the secret message. In this paper, we present a powerful new blind steganalytic scheme that can reliably detect hidden data in JPEG images. This would increase the success rate of steganalysis by detecting data in transform as well as spatial domain. This scheme is feature based in the sense that features that are sensitive to embedding changes and being employed as means of steganalysis. The features are extracted in DCT domain. DCT domain features have extended DCT features and Markovian features merged together to eliminate the drawbacks of both. The blind steganalytic technique has a broad spectrum of analyzing different embedding techniques. The feature based steganalytic technique is used in the DCT domain to extract about 23 functionals and classify the dataset according to these functionals. The feature set can be increased to about 274 features by merging both DCT and Markovian features. The extracted features are being fed to a classifier which helps to distinguish between a cover and stego image. Support Vector Machine is used as classifier here.

Keywords: Steganalysis, DCT, Principal Component Analysis, Feature Extraction, Support Vector Machine