Narrow Results

The art of identifying steganographic traces from digital media images is termed steganalysis. The secret message embedded into the digital media files may be text, audio, video, or in the form of an image. The detection of secret hidden information from the images is carried out using Image steganalysis. The detection and extraction of existing hidden secret messages from the original image are difficult. Hence, an optimization-based deep learning model for detecting hidden information is designed here. In this research, the designed CAViaR Student Psychology-based Optimization-Deep Maxout Network (CSPBO-DMN) technique is used for recovery of the original image through steganography and steganalysis. The bit map image is generated from the cover image and the hidden secret message is XOR-ed with a key. Discrete wavelet transform (DWT)-based embedding, Least-significant bit (LSB)-based embedding and Discrete Cosine Transform (DCT)-based embedding techniques are the XOR-ed and bit map image output. Later, using the DMN classifier, the secret message is detected from the bit map image, which is trained using the CSPBO technique. The experimental outcomes proved that the CSPBO-DMN approach attained higher performance with a Peak-Signal-to-Noise Ratio (PSNR), Bit Error Ratio (BER), computational complexity and memory usage of 35.275 dB, 5.658, 1.225 and 0.017, respectively.

The typical model of steganography has led the prisoners' problem, in which two persons attempt to communicate covertly without alerting the warden, that is, only the receiver knows the existence of the message sent by the sender. One available way to achieve this task is to embed the message in an innocuous-looking medium. In this paper, we propose a variation of the Quantization Index Modulation (QIM) for solving the prisoners' problem. We also propose a theorem to show that the error of mean intensity value of an image block caused by JPEG compression is bounded. The proposed method embeds the messages to be conveyed by modifying the mean intensity value, and the resulting stego-image can be stored in the JPEG format with a low quality setting. Besides, a specific pattern caused by using the QIM embedding method is also identified, and this pattern will be removed using the proposed embedding method. Experimental results and the proposed theorem show that the hidden message is error-free against the JPEG distortion under the quality setting as low as 25. Furthermore, the existence of the hidden message is not only visually imperceptible but also statistically undetectable.

Recently, a large number of studies have shown that Convolutional Neural Networks are effective for learning features automatically for steganalysis. This paper uses the transfer learning method to help the training of CNNs for steganalysis. First, a Gaussian high-pass filter is designed for pretreatment of the images, that can enhance the weak stego noise in the stegos. Then, the classical Inception-V3 model is improved, and the improved network is used for steganalysis through the method of transfer learning. In order to test the effectiveness of the developed model, two spatial domain content-adaptive steganographic algorithms WOW and S-UNIWARD are used. The results imply that the proposed CNN achieves a better performance at low embedding rates compared with the SRM with ensemble classifiers and the SPAM implemented with a Gaussian SVM on BOSSbase. Finally, a steganalysis system based on the trained model was designed. Through experiments, the generalization ability of the system was tested and discussed.

Data hiding in the LSB of audio signals is an appealing steganographic method. This is due to the large volume of real-time production and transmission of audio data which makes it difficult to store and analyze these signals. Hence, steganalysis of audio signals requires online operations. Most of the existing steganalysis methods work on stored media files. In this paper, we present a steganalysis technique that can detect the existence of embedded data in the least significant bits of natural audio samples. The algorithm is designed to be simple, accurate, and to be hardware implementable. Hence, hardware implementation is presented for the proposed algorithm. The proposed hardware analyzes the histogram of an incoming stream of audio signals by using a sliding window strategy without needing the storage of the signals. The algorithm is mathematically modeled to show its capability to accurately predict the amount of embedding in an incoming stream of audio signals. Audio files with different amounts of embedded data were used to test the algorithm and its hardware implementation. The experimental results prove the functionality and high accuracy of the proposed method.

This paper presents methods for performing steganography and steganalysis using a statistical model of the cover medium. The methodology is general, and can be applied to virtually any type of media. It provides answers for some fundamental questions that have not been fully addressed by previous steganographic methods, such as how large a message can be hidden without risking detection by certain statistical methods, and how to achieve this maximum capacity. Current steganographic methods have been shown to be insecure against simple statistical attacks. Using the model-based methodology, an example steganography method is proposed for JPEG images that achieves a higher embedding efficiency and message capacity than previous methods while remaining secure against first order statistical attacks. A method is also described for defending against "blockiness" steganalysis attacks. Finally, a model-based steganalysis method is presented for estimating the length of messages hidden with Jsteg in JPEG images.

Securing the confidentiality of patient information using the image steganography process has gained more attention in the research community. However, embedding the patient information is a major task in the steganography process due to the complexity in identifying the pixel features. Thus, an effective Crow Search Algorithm-based deep belief network (CSA-DBN) is proposed for embedding the information in the medical image. Initially, the appropriate pixels and the features, like pixel coverage, wavelet energy, edge information, and texture features, such as local binary pattern (LBP) and local directional pattern (LDP), are extracted from each pixel. The proposed CSA-DBN utilizes the feature vector and identifies the suitable pixels used for embedding. The patient information is embedded into the image by using the embedding strength and the DWT coefficient. Finally, the embedded information is extracted using the DWT coefficient. The analysis of the proposed CSA-DBN approach is done based on the performance metrics, such as correlation coefficient, peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) that acquired the average values as 0.9471, 24.836dB, and 0.4916 in the presence of salt and pepper noise and 0.9741, 57.832dB, and 0.9766 in the absence of noise.