Print ISSN: 1811-9212

Online ISSN: 2617-3352

Keywords : steganography


Data Hiding by Unsupervised Machine Learning Using Clustering K-mean Technique

Hiba Hamdi Hassan; Maisa'a Abid Ali Khodher

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2021, Volume 21, Issue 4, Pages 37-49
DOI: https://doi.org/10.33103/uot.ijccce.21.4.4

Steganography includes hiding text, image, or any sentient information inside another image, video, or audio. It aims to increase individuals’ use of social media, the internet and web networks to securely transmit information between sender and receiver and an attacker will not be able to detect its information. The current article deals with steganography that can be used as machine learning method, it suggests a new method to hide data by using unsupervised machine learning (clustering k-mean algorithm). This system uses hidden data into the cover image, it consists of three steps: the first step divides the cover image into three clusterings that more contrast by using k-means cluster, the selects a text or image to be converted to binary by using ASCII code, the third step hides a binary message or binary image in the cover image by using sequential LSB method. After that, the system is implemented. The objective of the suggested system is obtained, using Unsupervised Machine Learning (K-mean technique) to securely send sensitive information without worrying about man-in-the-middle attack was proposed. Such a method is characterized by high security and capacity. Through evaluation, the system uses PSNR, MSE, Entropy, and Histogram to hide the secret message and secret image in the spatial domain in the cover image.

Comparison of Three Proposal Methods in Steganography Encryption Secret Message using PVD and MapReduce

Huda Ghazie Abd UL Sahib; Maisa Abid Ali Khodher

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2021, Volume 21, Issue 2, Pages 115-131

This paper will present a comparison between three proposed methods. All of these methods
include hiding a secret message inside a video for the aim of transferring it to another party with high
security and a high embedding rate in order to ensure that the secret message is not discovered by the
attacker. In addition , facilitating deals with video frames as large data for the purpose of analyzing,
dividing and controlling frames easily by the programmer, using the MapReduce method. This is
done by dividing the video into a series of frames, and before the hiding process, the message is
encrypted using the advance encryption standard (AES) algorithm. These basic processes are
implemented in all three proposed methods, the rest of the details for each method are:
The first method: used the pixel value difference (PVD) algorithm to hide the secret message in the
video. In addition, the stego secret key was also used. This key is used for the purpose of deciding the
locations of the pixels that will be employed to hide the secret message inside it.
The second method: the MapReduce principle is used for the purpose of facilitating dealing with
video frames. The chosen frame will enter the MapReduce stages. This is implemented by dividing the
frame into three matrices red, green, blue (RGB). Each matrix represents a map. Moreover, the
technique that is used for concealment is the least significant bit (LSB) technology which uses the
stego secret key (x2) for the purpose of selecting sites that will be hidden by it.
The third method: Also, the MapReduce principle is used, but this method is implemented by dividing
the frame into four blocks. Each block represents a map. In one of the stages of the MapReduce, the
hiding process will be done by using the (PVD) method which uses the stego secret key (n+15).
Finally, the reducer, which is the last stage, will collect the results of each block to generate the
stego-frame.
The results of the three methods are efficiency, transparency, robustness and powerful in stego
video. It is noticed that the second method has achieved the lowest capacity, thus achieving high
security. As for the third method, it achieved the highest capacity and the highest execution time was
the first method. Despite this, all the three methods have achieved high security. The attacker or
unauthorized person cannot detect any suspicious differences in a stego video. These results are
obtained through using many measurements: peak signal-to-noise ratio (PSNR), Mean Squared Error
(MSE), Entropy and correlation coefficient.

A Development of Least Significant Bit Steganography Technique

Mohammed Majid Msallam

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2020, Volume 20, Issue 1, Pages 31-39

Recently, the world has been interested in transferring data between different devices. The transmission of data must be encrypted so that the intended receiver can only read and process a secret message. Hence, the security of information has become more important than earlier. This paper proposes the least significant bit Steganography method to hide a secret message inside an image cover via using dynamic stego-key. To check the effectiveness of the proposed method, many factors are used for evaluation and compared with another method. The results illustrate more robustness at steganography since stego-key depends on the cover image to hide a secret message.

Design a Hybrid Cryptosystem Based Chaos and Sharing for Digital Audio

Mahmood Z. Abdullah; Zinah J. Khaleefah

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2017, Volume 17, Issue 1, Pages 59-70

With the growth rate of wireless communication with internet and
multimedia. The wireless network has expanded their applications in our life.
Cryptography and steganography play important role within data security. This
paper chiefly produces a novel hybrid cryptography and steganography for
digital audio base chaos system and secret sharing scheme algorithm. These
algorithms have multilevel of processing with the digital audio to increase the
level of security. In this algorithm, digital audio was encrypted with a novel
encryption method based Lorenz chaos map. Then, divide the encrypted audio
to N encrypted audio based on secret sharing scheme. Finally, hiding N
encrypted audio in N cover images with chaos system process. The result shows
that the algorithm for audio encryption have a high degree of confidence, large
key space reached more than 2672 possible of a key, key sensitivity, and high
quality of recovered digital audio. Chaos system and secret sharing process
with multi-cover images offers additional space, security for the secret audio
message, and quality for cover images. The power signal to noise ratio of cover
images reached to 57db with embedding 334 KB of secret audio with four cover
images.

A Technique for Image Steganography Based on Optimal Resilient Boolean Functions and DCT

Azhar Malik

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2013, Volume 13, Issue 2, Pages 71-80

Abstract:One of the methods introduced for accomplishing hidden communication
is the steganography technique. Steganography is an important area of research in recent
years involving a number of applications. It is the science of embedding information
into the cover image, text and video without causing statistically significant
modification to the cover image. This paper proposes an image steganography system; it
hides the gray level image on another gray level image by using optimal resilient
Boolean functions. First, it starts by encrypting secret image by using optimal resilient
function then embedding encrypted image inside a cover image by using DCT. The new
proposal system of image encryption has been investigated by encrypting the powerful
frequency coefficients in DCT using a saturated best resilient Boolean function (SRB)
that constructed by Zhang's construction. The simulation results of the proposal system
have calculated the peak signal to noise ratio (PSNR) and the correlation test in order to
compare between the cover image and the stego image and the results have also
calculated the correlation test between the secrete image and the extraction image as a
parameter of robustness. The experimental results have showed that the images can be
embedded by steganography and optimal resilient Boolean function with smaller
correlation compared to the original secret image and the extraction image. Finally, it is
observed that for all images, PSNR is greater than 55.

Information Hiding in Image Based on Random Locations

Mohsin H. AL-Zohairi

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2012, Volume 12, Issue 2, Pages 9-15

Abstract: Network Security for data transmission is the most vital issue in modern communication systems. This paper discusses a new steganographic technique and the effectiveness of the proposed method is described through which the idea of enhanced security of data can be achieved. To hide data in a binary image, the proposed method focuses on the Least Significant Bit (LSB) technique in hiding messages in an image. The proposed method enhanced the LSB technique by randomly dispersing the bits of the message in the image and thus making it harder for unauthorized people to extract the original message easily.

Improving Hiding Information Process based on GA Technique with Secure Extraction Process

Susan .S. Ghazoul; Lina Saeed Jajo

IRAQI JOURNAL OF COMPUTERS, COMMUNICATIONS, CONTROL AND SYSTEMS ENGINEERING, 2010, Volume 10, Issue 1, Pages 98-106

Abstract:
In this paper we propose a new method of hiding information that produces a stego-image which is totally indistinguishable from the original image to extract the hiding message. GA is used as an efficient method to minimize the number of different bits between the cover image and the stego-image as minimum as possible by embedding the message in random locations of cover image, and then modifying the locations containing changed information in original image (cover) to improve stego-image quality. To satisfy excellent security we used a crypto-key which contains encrypted locations from hiding process. This key is used to extract the embedded message.