JPEG STATISTICAL DETECTION OF STEGANOGRAPHIC MESSAGES
Abstract
The subject of this work done is digital steganography field, namely hidden messages detection in statical digital pictures problem. In this paper probability of hidden messages detection using statistical features distribution of discrete cosine transform coefficients for two steganographic algorithms was
checked. This data allow detecting JSTEG hidden messages and improving algorithm with image statistic
features considering. For this purpose two novel parameters: imbalance of container`s paired discrete cosine transform coefficients and imbalance of container`s discrete cosine transform coefficients least significant bits were determined. As steganographic containers, JPEG images were considered. These parameters
were measured for one thousand of empty containers samples and for equal quantity of containers with messages, hidden by JSTEG algorithm and by early proposed steganographic algorithm with container image
statistics accounting. Based on the received results, imbalance of container`s paired discrete cosine transform coefficients was chosen as a measured parameter for embedded message detection. Also measured parameter threshold was chosen on condition, that probability of type I and type II errors is equal. With this
parameter threshold value probability of type I and type II errors, probability of hidden messages detection
and statistical significance of chosen parameter α was calculated. Based on the received results, only JSTEG
hidden messages can be definitely detected by chosen parameter measurement. In considered publications,
histogram detection of hidden messages was principally described, so this work can offer alternate different
numerical parameter for JPEG steganalisys.