Image Steganography between Firefly and PSO Algorithms
By
*Ziyad Tariq Mustafa Al-Ta'i , *Jamal Mustafa Abass ,**Omar Y. Abd Al-
Hameed
* Department of Computer Science - College of Science - University of
Diyala
** Computer Science Department – University of Garmian
Abstract
Steganography is one type of security in the Internet world. However,
steganography methods have the disadvantage that once their method is
known, the embedded message can be deduced. Therefore, different techniques
are developed in order to strengthening steganographic algorithms, such as
swarm intelligence. This paper presents firefly and Particle Swarm
Optimization (PSO) algorithms for finding best positions inside image cover
in order to LSB embed text message. A comparison between these two
algorithms is given. Results prove that firefly algorithm is better than
PSO algorithm for image steganography.
In the growing linked modern world, one may wish to be able to protect
not only secrecy of the communication but also privacy of the
communicators. Obscure communication allows one to communicate without
revealing who is communicating [1]. Obscure communication, the onset of
computer technology and the Internet has given new life to information
hiding and the creative methods with which it is employed [2]. Information
hiding, in general, is covering sensitive information within normal
information. This creates a hidden communication channel between the sender
and receiver such that the existence of the channel is unnoticeable. Hidden
channels have advantages over the encrypted channels that the anonymity of
communication is protected [3]. Since the real pictures are much better
means of communications between human users, it is convenient to develop an
image steganographic systems[4].
Swarm Intelligence is part of artificial intelligence. It based on the
study of collective behavior in decentralized and self-organized
systems[5]. The idea of SI comes from systems found in nature, including
ant colonies, bird flocking and animal herding that can be effectively
applied to computationally intelligent system. Swarm Intelligence systems
are typically made up of a population of agents interacting locally with
one another and with their environment and local interactions between such
nodes often lead to the emergence of a global behavior[6]. Particle swarm
optimization (PSO) and firefly algorithm are used as powerful swarm
intelligence search techniques finding best steganographic positions[5].
2. Particle Swarm Optimization (PSO)
The basic PSO model consists of a swarm of particles, which are
initialized with a population of random candidate solutions. They move
iteratively through the d-dimension problem space to search for the new
solutions, where the fitness, f, can be calculated as the certain qualities
measure[7].
Each particle has a position represented by a position-vector xi (i
is the index of the particle), and a velocity represented by a velocity-
vector vi. Each particle remembers its own best position so far in a vector
i-th, and its d-dimensional value is pbest(pid).
The best position-vector among the swarm so far is then stored in the
vector i-th, and its d-th dimensional value is gbest(pgd). During the
iteration time t, the update of the velocity (vid) from the previous
velocity to the new velocity is determined by Eq. (1). The new position
(xid) is then determined by the sum of the previous position and the new
velocity by Eq. (2).
where i =1,2,…..,N; w is the inertia weight, r1 and r2 are the random
numbers, which are used to maintain the diversity of the population, and
are uniformly distributed in the interval [0,1] for the d-th dimension of
the i-th particle. c1 is a positive constant, called coefficient of the
self recognition component; c2 is a positive constant, called coefficient
of the social component. The general basic algorithm for the Particle Swarm
Optimization can be described in algorithm (1) [8].
3. Firefly Algorithm
The firefly algorithm is based on idealized behavior of the flashing
characteristics of fireflies[9]. For simplicity, we can summarize these
flashing characteristics as the following three rules: All fireflies are
unisex, so that one firefly is attracted to other fireflies regardless of
their sex. Attractiveness is proportional to their brightness, thus for any
two flashing fireflies, the less bright one will move towards the brighter
one. The attractiveness is proportional to the brightness and they both
decrease as their distance increases. If no one is brighter than a
particular firefly, it will move randomly. The brightness of a firefly is
affected or determined by the landscape of the objective function to be
optimized [10]. Based on these three rules, the basic steps of the firefly
algorithm (FA) can be summarized as shown in algorithm (2) [11].
4. The Proposed System
For comparison purposes the proposed system is done twice: first with
firefly algorithm ; second with PSO algorithm, as shown in subsections (4.1
and 4.2).
4.1 Steganography Using Firefly Algorithm
Figure (1 and 2) show the block diagram of hiding text message inside
image cover image using firefly algorithm (depending on algorithm (2)) with
least significant bit (LSB) technique .
Figure (1) Block Diagram of Hiding text message Inside Cover
Image Using Firefly Algorithm with LSB Technique
Figure (2) Block Diagram of Firefly Algorithm for Finding
Best Hiding Location in Cover Image
At receiver stage; stego image is received, and text message is
extracted. The first step is applying firefly algorithm on stego image (as
shown in figure (2)), in order to find hiding locations (pixels).The blue
color in specified pixels is splitted and converted to binary form. Hence,
the secret text message is extracted using LSB technique (taking last bits
from specified binary values).
4.2 Steganography Using PSO Algorithm
Figure (3 and 4) show the block diagram of hiding text message inside
image cover image using PSO algorithm (depending on algorithm (1)) with
least significant bit (LSB) technique .
Figure (3) Block Diagram of Hiding text message Inside Cover
Image Using PSO Algorithm with LSB Technique
Figure (4) Block Diagram of PSO Algorithm for Finding
Best Hiding Location in Cover Image
5. Results
Figure (5) shows the relationship between the locations and the values
that are selected by the firefly and PSO algorithms.
(a) (b)
Figure (5) Relation Between Locations and Values of (a) Firefly Algorithm;
and (b) PSO Algorithm
Figure (6) shows (3) cover images with and without the location that
are selected by the firefly and PSO algorithms. Note that the selected
Locations are specified by green color.
Figure(6) Cover Images with and without Selected Locations by Firefly and
PSO Algorithms
The MSE and PSNR are calculated between the original cover images
and the stego covers at figure (7) and figure (8). These quality metrics of
these stegocovers are shown in table (1).
The results of this work show that both firefly and PSO algorithms are
good search techniques. However, from steganography point of view, firefly
algorithm is better than PSO algorithm for these reasons:
1- Firefly algorithm selects the best hiding positions as shown in figures
(5 and 6). These figures show that firefly hiding positions are deployed
all over the cover images, while PSO hiding positions are concentrated
in specific locations.
2- Table (1) shows that the firefly stegocovers have better quality metrics
than PSO stegocovers.
References
1- Ziyad Tariq Mustafa Al-Ta'i, " Development of Multilayer New Covert
Audio Cryptographic Model ", International Journal of Machine Learning
and Computing, Vol. 1, No. 2, June 2011.
2- F. N. Johnson, D. Zoran and J. Sushil "Information Hiding: Steganography
and Watermarking - Attacks and Countermeasures", Kluwer Academic
Publishers, Advances in Information Security, 2001, ch. 1.
3- Tri Van Le, "Covert Cryptography", Ms.c Thesis, The University of
Wisconsin-Milwaukee, August 1999, Abstract .
4- Ziyad Tariq Mustafa Al-Ta'i, " Simulation of New Covert Audio
Cryptographic Model", 3rd International Conference on Machine Learning
and Computing (ICMLC 2011), Singapore, 26-28 February 2011.
5- Ziyad Tariq Mustafa Al-Ta'i and Omer Younis Abd Al-Hameed , "Comparison
between PSO and Firefly Algorithms in Fingerprint Authentication",
International Journal of Engineering and Innovative Technology (IJEIT)
, Volume 3, Issue 1, July 2013.
6- Bonabeau, Dorigo M., and Theraulaz G., "Swarm Intelligence: From
Natural to Artificial Systems", book from Oxford University Press,
1999.
7- Kennedy J. and Eberhart R. C., "Particle Swarm Optimization",
Proceedings of the 1995 IEEE International Conference on Neural
Networks, volume 4, PP: 1942–1948, Australia, IEEE Service Center,
1995.
8- Ismail Khalil Ali, " Intelligent Cryptanalysis Tool Using Particle Swarm
Optimization", Ph.D.Thesis, Univercity of Technology, Department of
Computer Science, Iraq, 2009.
9- Sh. M. Farahani, A. A. Abshouri, B. Nasiri, and M. R. Meybodi, " A
Gaussian Firefly Algorithm", International Journal of Machine Learning
and Computing, December 2011.
10- Xin-She Yang, "Nature-Inspired Metaheuristic Algorithms" Book
from Luniver Press, united kingdom, 2008.
11- N. Chai-ead, P. Aungkulanon, and P. Luangpaiboon, "Bees and Firefly
Algorithms for Noisy Non-Linear Optimisation Problems", Proceeding of
the international Multi Conference of Engineers and Computer
Scientists, 2011.
Comments
Report "Image Steganography Between PSO and Firefly Algorithms.doc "