A Secure Spatial Domain Image Steganography Using Genetic Algorithm and Linear Congruential Generator

Abstract

Significant increase in data traffic over the Internet has given rise to many data security issues. Steganography is a technique which is used to hide the existence of secret communication. Hence, it is extensively used to solve the issues related to data security. In this paper, a secure and lossless spatial domain image steganography technique is proposed. Stream of secret data is hidden in quarter part of image by identifying suitable locations to hide 2 bits of secret data in each pixel, resulting in generation of coefficients corresponding to the location of match. These coefficients are hidden in remaining part of image using LSB replacement steganography. Genetic algorithm is used to find best possible location to hide these coefficients in the image, making the proposed technique very secure and almost impossible to extract secret data from it. The result of the proposed technique is compared with LSB replacement steganography where in same amount of secret data is embedded. It is observed that the proposed technique is much superior as compared to LSB steganography. It provides improvement in MSE and PSNR values; in addition, the degradation in histogram is also minimal thus eliminating histogram attack. Average PSNR value of stego-image obtained from proposed technique is 53.11 dB at two bits per pixel data embedding rate compared to 52.21 obtained by LSB technique.