• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.11
• /
• pp.4153-4169
• /
• 2014

To recognize F5-like (such as F5 and nsF5) steganographic algorithm from multi-class stego images, a recognition algorithm based on the identifiable statistical feature (IDSF) of F5-like steganography is proposed in this paper. First, this paper analyzes the special modification ways of F5-like steganography to image data, as well as the special changes of statistical properties of image data caused by the modifications. And then, by constructing appropriate feature extraction sources, the IDSF of F5-like steganography distinguished from others is extracted. Lastly, based on the extracted IDSFs and combined with the training of SVM (Support Vector Machine) classifier, a recognition algorithm is presented to recognize F5-like stego images from images set consisting of a large number of multi-class stego images. A series of experimental results based on the detection of five types of typical JPEG steganography (namely F5, nsF5, JSteg, Steghide and Outguess) indicate that, the proposed algorithm can distinguish F5-like stego images reliably from multi-class stego images generated by the steganography mentioned above. Furthermore, even if the types of some detected stego images are unknown, the proposed algorithm can still recognize F5-like stego images correctly with high accuracy.

• Journal of Korea Multimedia Society
• /
• v.24 no.4
• /
• pp.550-557
• /
• 2021

Image steganalysis is a technique for detecting images with steganographic algorithms applied, called stego images. With state-of-the-art CNN-based steganalysis methods, we can detect stego images with high accuracy, but it is not possible to know which steganographic algorithm is used. Identifying stego images is essential for extracting embedded data. In this paper, as the first step for extracting data from stego images, we propose a hierarchical CNN structure for senary classification of steganographic algorithms. The hierarchical CNN structure consists of multiple CNN networks which are trained to classify each steganographic algorithm and performs binary or ternary classification. Thus, it classifies multiple steganogrphic algorithms hierarchically and stepwise, rather than classifying them at the same time. In experiments of comparing with several conventional methods, including those of classifying multiple steganographic algorithms at the same time, it is verified that using the hierarchical CNN structure can greatly improve the classification accuracy.

• Journal of Korea Society of Industrial Information Systems
• /
• v.14 no.3
• /
• pp.37-43
• /
• 2009

Steganography conceals the fact that hidden message is being sent on the internet. Steganalysis can be detected the abrupt changes in the statistics of a stego-data. After message embedding, I have analyzed for the statistical significance of the fact the occurrence of differences among the four-neighboring pixels. In this case, when a embedding messages within a images is small, use EC value and chi-square test to determine whether a distribution in an images matches a distribution that shows distortion from stego-data.

• KIISE Transactions on Computing Practices
• /
• v.23 no.4
• /
• pp.244-249
• /
• 2017

Steganalysis is to detect information hidden by steganography inside general data such as images. There are stegoanalysis techniques that use machine learning (ML). Existing ML approaches to steganalysis are based on extracting features from stego images and modeling them. Recently deep learning-based methodologies have shown significant improvements in detection accuracy. However, all the existing methods, including deep learning-based ones, have a critical limitation in that they can only detect stego images that are created by a specific steganography method. In this paper, we propose a generalized steganalysis method that can model multiple types of stego images using deep learning. Through various experiments, we confirm the effectiveness of our approach and envision directions for future research. In particular, we show that our method can detect each type of steganography with the same level of accuracy as that of a steganalysis method dedicated to that type of steganography, thereby demonstrating the general applicability of our approach to multiple types of stego images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.2
• /
• pp.457-476
• /
• 2011

This paper presents an improved XOR-based Data Hiding Scheme (XDHS) to hide a halftone image in more than two halftone stego images. The hamming weight and hamming distance is a very important parameter affecting the quality of a halftone image. For this reason, we proposed a method that involves minimizing the hamming weights and hamming distances between the stego image and cover image in $2{\times}2$-pixel grids. Moreover, our XDHS adopts a block-wise operation to improve the quality of a halftone image and stego images. Furthermore, our scheme improves security by using a block-wise operation with A-patterns and B-patterns. Our XDHS method achieves a high quality with good security compared to the prior arts. An experiment verified the superiority of our XDHS compared with previous methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.94-101
• /
• 2012

This paper proposes an improved image steganalysis scheme to raise the detection rate of stego images out of cover images. To improve the detection rate of stego image in the steganalysis, tiny variation caused by data hiding should be amplified. For this, we extract feature vectors of cover image and stego image by two steps. First, we separate image into upper 4 bit subimage and lower 4 bit subimage. As a result, stego noise is expanded more than two times. We decompose separated subimages into twelve subbands by applying 3-level Haar wavelet transform and calculate co-occurrence probabilities of two different subbands in the same scale. Since co-occurrence probability of the two wavelet subbands is affected by data hiding, it can be used as a feature to differentiate cover images and stego images. The extracted feature vectors are used as the input to the multilayer perceptron(MLP) classifier to distinguish between cover and stego images. We test the performance of the proposed scheme over various embedding rates by the LSB, S-tool, COX's SS, and F5 embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.3
• /
• pp.482-491
• /
• 2011

The purpose of this study is to design and implement a 2-level secret information transmission system which can be used for information hiding of images transmitted over various IT communication media. To increase the robustness of the hiding power, we combined the steganography method which inserts secret object into cover object to hide the very fact of information hiding itself, and the preprocessing stage to encrypt the secret object before the stego-insertion stage. As a result, even when the stego-image is broken by an attacker, the secret image is protected by encryption. We implemented the 2-level image insertion and extraction algorithm by using C++ programming language. Experiment shows that the PSNR values of stego-images of ours exceed 30.00db which is the threshold of human recognition. The methodology of this study can be applied broadly to the information hiding and protection of the military secret images.

• Journal of Korea Multimedia Society
• /
• v.8 no.3
• /
• pp.379-388
• /
• 2005

Image steganography Is a secret communication scheme to transmit a secret message, which is embedded into an image. The original image and the embedded image are called the cover image and the stego image, respectively. In other words, a sender embeds a secret message into a cover image and transmits a stego image to a receiver, while the receiver takes the stego image, extracts the message from it, and reads the message. General requirements for steganography are great capacity of secret messages, imperceptibility of stego images, and confidentiality between a sender and a receiver. In this paper, we propose a method for being satisfied with three requirements. In order to hide a secret message into a cover image safely, we use a difference value of two consecutive pixels and a secret quantization range. The former is used for the imperceptibility and the latter for the confidentiality. Furthermore, the number of insertion bits is changed according to the difference value for the imperceptibility. Through experiments, we have shown that our method is more good quality of stego images than many other related methods and increases the amount o( message insertion by performing dual insertion processing for some pixels.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.395-413
• /
• 2016

Image authentication is a technique aiming at protecting the integrity of digital images. Reversible image authentication has attracted much attention of researcher because it allows to authenticate tampered regions in the image and to reconstruct the stego image to its original version losslessly. In this paper, we propose a new, reversible image authentication scheme based on adaptive prediction error expansion (PEE) technique. In the proposed scheme, each image block is classified into smooth or complex regions. Then, according to the characteristic of each block, the authentication code is embedded adaptively to achieve high performance of tamper detection. The experimental results demonstrated that the proposed scheme achieves good quality of stego images. In addition, the proposed scheme has ability to reconstruct the stego image to its original version, if no modification is performed on it. Also demonstrated in the experimental results, the proposed scheme provides higher accuracy of tamper detection than state-of-the-art schemes.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.180-186
• /
• 2013

The primary goal of attack on steganographic images, termed steganalysis, is to detect the presence of hidden data by finding statistical abnormality of a stego-media caused by data embedding. This paper proposes a novel steganographic scheme based on improving the (7, 4) Hamming code for digital images. The proposed scheme embeds a segment of six secret bits into a group of nine cover pixels at a time. The experimental results show that the proposed scheme achieves a 0.67bpp embedding payload and a slightly higher visual quality of stego images compared with the previous arts.