Image steganographic scheme based on pixel-value differencing and LSB replacement methods

This paper provides a result assessment of traditional JPEG picture extraction function steganalysis compared to a cross-validation picture. Four distinct algorithms are used as steganographic systems in the spatial and transform domain. They are LSB Matching, LSB Replacement, Pixel Value Differencing and F5.A 25 percentage of embedding with text embedding information is considered in this paper. The characteristics regarded for evaluation are the First Order, Second Order, Extended DCT characteristics, and Markov characteristics. Support Vector Machine is the classifier used here. In statistical recovery, six distinct kernels and four distinct sampling techniques are used for evaluation.

Download Full-text

Blind Steganalysis for JPEG Images using SVM and SVM-PSO Classifiers

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.k1250.09811s19 ◽

2019 ◽

Vol 8 (11S) ◽

pp. 1239-1246 ◽

Cited By ~ 1

Keyword(s):

Kernel Functions ◽

Support Vector ◽

Least Significant Bit ◽

Jpeg Images ◽

Lsb Matching ◽

Universal Steganalysis ◽

Pixel Value ◽

Lsb Replacement ◽

Pixel Value Differencing ◽

Blind Steganalysis

Blind steganalysis or the universal steganalysis helps to identify hidden information without previous knowledge of the content or the embedding technique. The Support Vector Machine (SVM) and SVM- Particle Swarm Optimization (SVM-PSO) classifiers are adopted for the proposed blind steganalysis. The important features of the JPEG images are extracted using Discrete Cosine Transform (DCT). The kernel functions used for the classifiers in the proposed work are the linear, epanechnikov, multi-quadratic, radial, ANOVA and polynomial. The proposed work uses linear, shuffle, stratified and automatic sampling techniques. The proposed work employs four techniques for image embedding namely, Least Significant Bit (LSB) Matching, LSB replacement, Pixel Value Differencing (PVD) and F5 and applies 25% embedding. The data to the classifier is split as 80:20 for training and testing and 10-fold cross validation is carried out.

Download Full-text

High-capacity steganographic method based on pixel-value differencing and LSB replacement methods

The Imaging Science Journal ◽

10.1179/136821910x12651933390584 ◽

2010 ◽

Vol 58 (4) ◽

pp. 213-221 ◽

Cited By ~ 8

Author(s):

Ki-Hyun Jung

Keyword(s):

High Capacity ◽

Pixel Value ◽

Lsb Replacement ◽

Pixel Value Differencing

Download Full-text

TEKNIK PENYEMBUNYIAN PESAN TEKS TERENKRIPSI ALGORITMA MERKLE-HELLMAN KNAPSACK MENGGUNAKAN METODE PIXEL VALUE DIFFERENCING KE DALAM CITRA DIGITAL

KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) ◽

10.30865/komik.v3i1.1590 ◽

2019 ◽

Vol 3 (1) ◽

Author(s):

Agung Lestari ◽

Abdul Sani Sembiring ◽

Taronisokhi Zebua

Keyword(s):

Digital Image ◽

Data Security ◽

Object Based ◽

Pixel Value ◽

Attack Data ◽

Pixel Value Differencing ◽

Knapsack Algorithm ◽

Cryptographic Techniques

Optimization of data security techniques is very necessary so that the data or information that is secured is really safe from attack. Data that has been encrypted based on cryptographic techniques very quickly raises suspicion that the data is confidential or important. Therefore, this technique is better combined with steganography techniques. Utilization of steganography techniques can minimize the attacker's suspicion of data that is secured, because by using steganography data techniques can be hidden on certain objects. This study discusses how to encode a text based on the Merkle-Hellman Knapsack algorithm and the resulting password is hidden in a grayscale digital image as a hiding object based on the pixel value differencing algorithm. This is done to minimize suspicion and make it difficult for attackers to find out confidential or important data.Keywords: cryptography,steganography, merkle-hellmankanpsack, PVD, image

Download Full-text