Blind steganalytic attack as pattern recognition, using ROC for distance calculation in k-Nearest neighbour Classification Technique

Steganographic techniques are used to hide the existence of the messages. An advantage of steganography is that it can be employed to secretly transmit messages without the fact of the transmission being discovered. Steganalysis is the mechanism of detecting the presence of hidden information in the stego media and it allows an adversary to use steganalytic techniques to reveal that a secret communication is taking place. Steganalysis can be a targeted steganalysis or a blind steganalysis. In the existing method, multi-class steganalysis classification technique is used to detect low embedded capacity. In this paper, a new multi-class steganalysis classification technique is implemented to detect the high embedded capacity with detection accuracy of atleast 95% with textual or a mixture of textual and graphic images using k-Nearest neighbor Classification Technique in which Receiver Operating Characteristics (ROC)curve is used to calculate the distance function for improving the used classification technique.