Information Hiding Using Ant Colony Optimization Algorithm

Information Hiding Using Ant Colony Optimization Algorithm

Wasan Shaker Awad (University of Bahrain, Bahrain)
Copyright: © 2011 |Pages: 13
DOI: 10.4018/jtd.2011010102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

This paper aims to find an effective and efficient information hiding method used for protecting secret information by embedding it in a cover media such as images. Finding the optimal set of the image pixel bits to be substituted by the secret message bits, such that the cover image is of high quality, is a complex process and there is an exponential number of feasible solutions. Two new ant-based algorithms are proposed and compared with other algorithms. The experimental results show that ant colony optimization algorithm can find the solution efficiently and effectively by finding the optimal set of pixel bits in a few number of iterations and with least Mean Square Error (MSE) comparable with genetic and genetic simulated annealing algorithms.
Article Preview

1. Introduction

Steganography (information hiding) is a technique to hide secret messages in a host media called cover media. In today’s world of digital communication, this is accomplished by embedding the covert message in a carrier medium such as an image, video, or sound file. The goal of steganography is not only to ensure secret messages transferred secretly, but also to make the transferred secret messages undetectable. It is the art of invisible communication, and provides a plausible deniability to secret communication. Steganography takes advantage of the inherent weaknesses of human perception by subtly altering the characteristics of the carrier (Cheddad, Curran & Kevitt, 2010; Ge, Gao & Wang, 2007; Di et al., 2003).

The basic structure of steganography is made up of three components: the carrier, the message, and the key. The carrier can be a painting, a digital image, or an mp3; it is the object that will ‘carry’ the hidden message. A key is used to decode/decipher/discover the hidden message (Nabavian, 2010).

In image steganography almost all data hiding techniques try to alter insignificant information in the cover image. For instance, a simple scheme proposed by Lee and Chen (2000), is to place the embedding data at Least Significant Bit (LSB) of each pixel in the cover image. The altered image is called stego-image. Altering LSB doesn’t change the quality of image to human perception but this scheme is sensitive a variety of image processing attacks like compression, cropping etc. The LSB insertion methods are common due to their simplicity and large capacity.

In order to overcome the problem of LSB technique of robustness, many researchers proposed different techniques to hide data in higher LSB layer (Chan & Chang, 2001; Chi-Kwong & Cheng, 2004; Chi-Shiang, 2009). Many other genetic algorithm (GA) based approaches to information hiding have been proposed (Chan & Lyu, 2005; Maity & Nandi, 2004; Wang, Yang, & Niu, 2010; Mazdak et al., 2009; Fard et al., 2006). Also, in 2010, Ching-Sheng and Shu-Fen utilized Ant Colony Optimization (ACO) algorithm to construct an optimal LSB substitution matrix.

All previous stego methods are homogenous, in which the same bit positions in the pixels of the cover image are used. For example in the LSB method, only least significant bits are used to hide data, but it has been shown that this method is weak in term of security. Also, using higher layers will affect the quality of the cover images. Thus, in order to overcome the problems of the previous methods, a new stego class has been proposed in by Awad and Jubori (2010), which is called non-homogeneous, in which the secret data can be hidden in different bit positions of different pixels. Also, a Genetic Simulated Annealing algorithm (GSA) has been proposed for non-homogeneous information hiding. This algorithm, as has been shown by the experimental results, is effective but inefficient because of the need for long chromosomes, large population size, and large number of generations to find the optimal solution.

In this paper, different techniques are employed, and a number of algorithms are presented and studied for hiding secret information using images. The techniques used are GA and ACO, and three algorithms are proposed: GA-GA, Random-ACO, and GA-ACO. Thus, the objectives of this work are:

  • Designing an efficient and effective algorithm for information hiding.

  • To compare between GA and ACO in terms of efficiency and effectiveness in solving the information hiding problem.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing