A New Convolutional Neural Network-Based Steganalysis Method for Content-Adaptive Image Steganography in the Spatial Domain

Sharma

International Journal of Digital Crime and Forensics

et al. 2023

The development of deep convolutional neural networks has been largely responsible for the significant strides forward made in steganography over the past decade. In the field of image steganography, generative adversarial networks (GAN) are becoming increasingly popular. This study describes current development in image steganographic systems based on deep learning. The authors' goal is to lay out the various works that have been done in image steganography using deep learning techniques and provide some notes on the various methods. This study proposed a result that could open up some new avenues for future research in deep learning based on image steganographic methods. These new avenues could be explored in the future. Moreover, the pros and cons of current methods are laid out with several promising directions to define problems that researchers can work on in future research avenues.

Section: Convolutional Neural Network Based Learning Steganographic A...mentioning

confidence: 99%

Latest Trends in Deep Learning Techniques for Image Steganography

Sharma

International Journal of Digital Crime and Forensics

et al. 2023

“…The proposed convolutional neural network block diagram is displayed in Figure 6 after considering the previous literature and the above discussion. In most of the previous CNN based techniques [27,[30][31][32][33][34], the SRM filters [11] were used as preprocessing layers in the CNN. In this paper, two preprocessing layers were used for revealing the stego-noise effectively.…”

Section: The Proposed Schemementioning

confidence: 99%

“…In CNN, bottleneck and spatial pyramid pooling were introduced for the better detection of HILL, S-UNIWARD, and WOW stego-images. Xiang et al [33] claimed better results on S-UNIWARD and WOW by changing the arrangements of the layers. The preprocessing was performed using thirty SRM filters.…”

Section: Introductionmentioning

confidence: 99%

Steganalysis of Context-Aware Image Steganography Techniques Using Convolutional Neural Network

2022

Image steganography is applied to hide some secret information. Occasionally, steganography is used for malicious purposes to hide inappropriate information. In this paper, a new deep neural network was proposed to detect context-aware steganography techniques. In the proposed scheme, a high-boost filter was applied to alleviate the high-frequency while retaining the low-frequency details. The high-boost image was processed by thirty SRM high-pass filters to obtain thirty high-boost SRM filtered images. In the proposed CNN, two skip connections were used to collect information from multiple connections simultaneously. A clipped ReLU layer was considered in spite of the general ReLU layer. In constructing the CNN, a bottleneck approach was followed for an effective convolution. Only a single global average pooling layer was used to retain the complete flow of information. SVM was utilized instead of the softmax classifier to improve the detection accuracy. In the experimental results, the proposed technique was better than the existing techniques in terms of the detection accuracy and computational cost. The proposed scheme was verified on BOWS2 and BOSSBase datasets for the HILL, S-UNIWARD, and WOW context-aware steganography algorithms.

“…One of the most used types of data hiding is image steganography, which involves the hiding of secret information within an image. In recent years, researchers have been exploring the use of chaotic systems to improve the security and robustness of image steganography [3] [4]. Chaotic systems are a type of dynamic system that exhibit complex, unpredictable behavior.…”

Section: Introductionmentioning

confidence: 99%

Image hiding in audio file using chaotic method

Hasan¹,

Kadim²,

Jaber³

et al. 2023

PEN

In this paper, we propose an efficient image hiding method that combines image encryption and chaotic mapping to introduce adaptive data hiding for improving the security and robustness of image data hiding in cover audio. The feasibility of using chaotic maps to hide encrypted image in the high frequency band of the audio is investigated. The proposed method was based on hiding the image data in the noisiest part of the audio, which is the high frequency band that was extracted by the zero crossing filter. Six types of digital images were used, each of size fit the length of used audio, this to facilitate the process of hiding them among the audio samples. The input image was encrypted by a one-time pad method, then its bits were hidden in the audio by the chaotic map. The process of retrieving the image from the audio was in the opposite way, where the image data was extracted from the high frequency band of the audio file, and then the extracted image was decrypted to produce the retrieved image. Four qualitative metrics were used to evaluate the hiding method in two paths: the first depends on comparing the retrieved image with the original image, while the second depends on comparing the audio containing the image data with the original audio once, and another time by comparing the cover audio with the original audio. The results of the quality metrics proved the efficiency of the proposed method, and it showed a slight and unnoticed effect between the research materials, which indicates the success of the hiding process and the validity of the research path.