Steganalysis Method Research Articles

SteriCNN: Cloud native stego content sterilization framework

Modern robust steganography-based cyber attacks often bypass intrinsic cloud security measures, and contemporary steganalysis methods struggle to address these covert threats due to recent advancements in deep learning (DL)-based steganography techniques. Existing steganography removal methods are constrained by trade-offs involving high processing times, poor quality of sanitized images, and insufficient removal of steganographic content. This paper introduces SteriCNN, a lightweight deep residual neural network model designed for steganography removal. SteriCNN effectively eliminates embedded steganographic information while preserving the visual integrity of the sanitized images. We employ a series of convolutional blocks with three residual connections for feature extraction, feature learning, feature attention, and image reconstruction from the residue. The proposed model utilizes the correlation of channel features to achieve a faster learning rate, and by varying the dilation rate in convolutional blocks, the model achieves wider receptive fields, enabling it to cover larger areas of the input image at each layer. SteriCNN is targeted for blind image sterilization for real-time use cases due to its low training and prediction time costs. Our study shows impressive results for both traditional and deep learning-based stego vulnerabilities, with approximately 90% of steganograms eliminated while maintaining an average PSNR value of 46 dB and an SSIM of 0.99 when tested with popular steganography methods.

Image Steganography Approaches and Their Detection Strategies: A Survey

Steganography is the art and science of hidden (or covered) communication. In digital steganography, the bits of image, video, audio and text files are tweaked to represent the information to hide. This article covers the current methods for hiding information in images, alongside steganalysis methods that aim to detect the presence of steganography. By reviewing 456 references, this article discusses the different approaches that can be taken toward steganography and its much less widely studied counterpart. Currently in research older steganography approaches are more widely used than newer methods even though these show greater potential. New methods do have flaws; therefore, more research is needed to make these practically applicable. For steganalysis one of the greatest challenges is the generalisability. Often one scheme can detect the presence of one specific hiding method. More research is needed to combine current schemes and/or create new generalisable schemes. To allow readers to compare results between different papers in our work, performance indications of all steganalysis methods are outlined and a comparison of performance is included. This comparison is given using ‘topological sorting’ graphs, which compares detection results from all papers (as stated in the papers themselves) on different steganographic schemes.

HGNN: A Hybrid Graph Neural Network Based on Transfer Learning for Linguistic Steganalysis

Steganography, especially in the form of text generation based on secret messages, has become a current research topic. It is more difficult to identify the hidden message when it embedded directly into the text without using a cover text, and it also has a higher embedding capacity. Owing to the high rate of imperceptibility and resistance to steganalysis of this type steganography, it is essential that steganalysis methods, generate better performance. Although the complexity of deep learning models increases the accuracy rate, it also increases the inference time. In this study, a linguistic steganalysis was performed with a lower inference time and a higher accuracy rate. In the developed model, first, differences between non-stega and steganographic texts were modelled by a finetuned Bert using the custom dataset. The disparity information obtained by fine-tuned model was distilled into 3 separate networks, BertGCN, BertGAT and BertGIN, for faster and more accurate inference. Then, these 3 distilled networks were combined through Transfer Learning to form a new model. Experiments demonstrates that the proposed model surpass other methods in terms of the accuracy (a success of 0.9879 at 3.22 bpw on text encoded through SAAC Encoding) and the effectiveness of inference (1.09 second).

Novel Steganalysis Method for Stego-Images Directly Constructed from Color Images Based on Their Quantum Noise

Novel Steganalysis Method for Stego-Images Directly Constructed from Color Images Based on Their Quantum Noise

Enhancing the performance of convolutional neural network image-based steganalysis in spatial domain using Spatial Rich Model and 2D Gabor filters

Image-based steganalysis problem has attracted many researchers, and several solutions have been proposed. Deep learning-based methods are the most promising as they provide superior performance. Convolutional Neural network(CNN) based steganalysis methods are designed to improve the detection rate. Unlike traditional CNN models, CNN-based steganalysis requires careful design of preprocessing layers with filter initialization to obtain a good performance. In this paper, we established a CNN model that consists of two convolution layers for preprocessing and feature extraction, and four fully connected layers for classification. The preprocessing layer uses a set of efficient filter banks consisting of SRM and 2D Gabor filters. We conducted experiments using grayscale cover images from a popular and publicly available BOSSbase_1.01 database and Alask_v2 database with consideration for two different image sizes. The results showed that the proposed CNN model outperforms many state-of-the-art studies in two out of three well-known adaptive spatial domain steganography algorithms (S-UNIWARD, HUGO) and provides a close result for (WOW) algorithm when using the database with 512 × 512 images. On the other hand, the proposed model outperforms many state-of-the-art studies in the three algorithms when using the database with the original image size (256 × 256). Using image size 256, and the S-UNIWARD algorithm, the proposed model improved the detection accuracy rate by 13%, and 4.25% payloads of 0.2 and 0.4 bpp respectively compared to the previously best-known model (GBRAS-Net). The proposed model achieved 7.4% and 6.27% improvement in the detection accuracy for both payloads 0.2 and 0.4 bpp respectively using the HUGO algorithm compared with the previously best-known model (GBRAS-Net). For the WOW algorithm, the proposed model is slightly behind the best model (GBRAS-Net) but was able to obtain a close result for both payloads of 0.2 and 0.4 bpp, respectively. Using an image size of 512, the proposed model achieved 31.26%, 21.51%, 6.84%, 4.22%, and 1.96% improvement in the detection rate for the five payloads 0.1, 0.2, 0.3, 0.4, and 0.5 bpp respectively over S-UNIWARD algorithm compared to the previously best-known model (H-CNN). In addition, the proposed model achieved 27.60%, 23.69%, 12.66%, 5.27%, and 6.23% improved detection accuracy for the five payloads 0.1, 0.2, 0.3, 0.4, and 0.5 bpp respectively over HUGO algorithm compared with the previously best-known model (H-CNN). Finally, the proposed model provided 57.81%, 46.84%, 28.29%, 20.34%, and 13.79% improvement in the detection rate for the five payloads 0.1, 0.2, 0.3, 0.4, and 0.5 bpp respectively over WOW algorithm compared to the previously best-known model (H-CNN).

Linguistic steganalysis via multi-task with crossing generative-natural domain

In the real world, the sources of text often transcend the boundaries of generative and natural domains, which introduces challenges for existing linguistic steganalysis methods. The typical problem arises from the sample selection bias caused by training solely on a single-source domain, rendering the model incapable of inferencing across the entire generative-natural (GN) space. Moreover, there exists the problem of overlooking the sensitive discrepancies between generative text and natural text, which hampers model fitting. In this paper, we model steganalysis in a brand-new perspective by employing multi-task learning to build the main task and auxiliary tasks in the cross GN domain. The proposed Cross Generative-Natural Domain Multi-task Model (CG-NDMM) can concurrently address the two aforementioned issues through i) modeling steganalysis across the entire GN space, incorporating two auxiliary tasks alongside a main task, and ii) utilizing a feature representation transfer learning strategy to harmonize two sub-networks. Furthermore, we employ diverse steganography algorithms to construct the datasets, which comprise four types of texts (generative-cover, generative-steganographic, natural-cover, and natural-steganographic) derived from two public datasets, Movie and Twitter. The experiments on these datasets demonstrate the effectiveness of the proposed approach, showcasing its substantially superior performance over the comparative baseline methods.

A Review on Image Steganography Techniques

In contemporary times, the exploration of digital multimedia has transformed it into a reliable medium for secure communication. Steganography, the art of concealed communication through mediums like images, has emerged as a pivotal approach, countered by the opposing method of steganalysis for detecting embedded data. This review delves into diverse methodologies examined by researchers, elucidating the primary objective of image steganography—to safeguard data messages from illicit access. The essence lies in discreetly transferring embedded secure data to the target destination without detection by unauthorized users. While various carrier file formats can be employed, digital images, owing to their widespread use on the global Internet, become the preferred medium. The realm of steganographic methodologies encompasses a broad spectrum, varying in complexity, each with its distinct strengths and weaknesses. This exploration underscores the dynamic landscape of image steganography, affirming the ongoing pursuit of effective methods to protect information from unauthorized access through covert channels. The review article provides an overview of various methodologies employed by researchers in the field of image steganography. It emphasizes the significance of using digital images as carrier files due to their prevalence on the worldwide Internet. The content acknowledges the complexity of steganographic methods and highlights that each method has its own strengths and weaknesses. Overall, the discussion underscores the importance of exploring and analyzing these methodologies to enhance the effectiveness of image steganography in secure communication.

Multi-Modality Ensemble Distortion for Spatial Steganography With Dynamic Cost Correction

This paper tackles a recent challenge in designing an efficient steganographic distortion model, whose goal is to accurately measure the modification cost of a pixel and help design steganographic schemes with high undetectability. Existing distortion models mostly assume that different modification directions of a pixel have an identical cost value and that pixel modifications are independent. These assumptions, however, may not lead to good steganography design because the modification direction of neighbouring pixels may affect the cost measurement of the current pixel. To address this problem, we propose a new distortion calculation method using dynamic cost correction and multi-modality distortion ensemble. The proposed scheme first employs a given distortion model to generate the original cost map. The cost of each pixel is then dynamically adjusted with majority voting according to the modification directions of its neighbouring pixels. Furthermore, different distortion calculation models are integrated to make the final decision on the distortion of each pixel. Experimental results show that compared to existing additive distortion-based steganographic schemes and deep learning-based steganographic schemes, steganography using our proposed distortion model performs better when tested against state-of-the-art steganalysis methods.

Digital Steganography : A Comprehensive Study on Various Methods for Hiding Secret Data in a Cover file

This research paper offers an in-depth examination of digital steganography, with a focus on the diverse methodologies utilized for embedding secret data within cover files. Steganography, the practice of concealing information within other non-secret data, ensures the hidden message remains undetectable to unauthorized observers. This study systematically reviews both traditional and modern steganographic techniques, dissecting their fundamental mechanisms, advantages, and weaknesses. Techniques explored include Least Significant Bit (LSB) insertion, discrete cosine transform (DCT), discrete wavelet transform (DWT), and innovative methods leveraging deep learning and adaptive algorithms. Each method is assessed for its imperceptibility, robustness, and data capacity, offering a comparative analysis to underscore their respective practical applications and limitations. Additionally, the paper delves into steganalysis—methods for detecting hidden information—to provide a comprehensive perspective on the field. Through experimental evaluation and theoretical analysis, this study seeks to enhance the understanding of digital steganography, presenting insights that could inform future research and the development of more secure data hiding techniques.

Lightweight JPEG image steganalysis using dilated blind-spot network

The primary goal of image steganalysis is to detect subtle steganographic signals hidden within digital images. An essential aspect of digital image steganalysis involves the extraction of meaningful steganographic signal features. However, existing JPEG steganalysis networks have not delved deep enough into the research on extracting steganographic noise signals, especially in the preprocessing stage of the model. In this paper, we propose a novel approach called the Dilated Blind-Spot Steganalysis Network (DBS2Net), specifically designed for JPEG steganalysis. DBS2Net incorporates the dilated blind-spot convolutional network into the preprocessing stage to extract noise residuals, thereby enhancing detection accuracy. The blind-spot network estimates central outputs based on adjacent regions to effectively suppress semantic information and uses dilated convolutions to expand the receptive field. Additionally, we design the transition block to further enhance noise signals by mapping noise residuals extracted by the blind-spot network. In feature extraction, depth-wise separable convolutions are used to minimize the parameter count, while dual-view pooling layers compress features, resulting in improved detection performance. Experimental results validate the efficacy of this approach, and comprehensive analyses of JPEG steganographic noise support its success. In particular, DBS2Net outperforms state-of-the-art steganalysis methods, achieving superior detection accuracy with minimal model complexity.

A Mathematical Formulation of Classified Variables for Enhanced Detection in Natural Language Steganalysis

Steganalysis, which is the counterpart to steganography, is an art and science that is devoted to detecting hidden information that has been concealed within seemingly harmless digital media. With the advancement in technology nowadays, the techniques used in steganography also become more complex, making it necessary to continuously improve steganalysis methods to keep up with emerging threats and ensure digital data's confidentiality, authenticity, and privacy. Steganalysts face the challenge of uncovering hidden information within covert media, requiring analysis of both original and altered media. While efficient steganalysis tools exist for specific approaches, devising a universal solution for all steganography techniques remains challenging. With the utilization of the formulated key, this paper aims to classify and analyze variables used in the steganalytic system. Thus, three views of classified variables are presented to address the pattern of detection. These are known as trade-off value-based, probability of character variable, and Support Vector Machine-based (SVM-based). Hence, it is expected that this scheme will become one of the alternative ways to enhance the steganalytic system for discovering the hidden message in communication. Furthermore, it is suggested the necessity for enhanced steganalysis techniques and tools, as well as the significance of academic and professional education in this area.

Quantum Reversible Audio Steganalysis Using Quantum Schmidt Decomposition and Quantum Support Vector Machine

With the development of various methods of quantum steganography, the discovery of these secret communications has become a necessity. This paper presents the first quantum steganalysis approach that uses statistical features of the quantum frequency domain to detect the steganographic methods in quantum communication networks. In this method, by proposing different quantum circuits, statistical features such as quantum mean, quantum square mean root, quantum variance, and quantum standard deviation are extracted to increase the accuracy of distinguishing between stego and clean signals. In the proposed method, the Schmidt coefficient vector extracted from the Quantum Haar Wavelet Transform (QHWT) is used to calculate the statistical features of the audio signal so that the main and dominant coefficients below the frequency sub-bands of the audio signal can be identified and selected. The proposed method uses a Quantum Support Vector Machine (QSVM) to classify the extracted feature vectors. The higher accuracy of the proposed frequency-based steganalysis method indicates its higher efficiency in detecting stego and clean signals than the quantum steganalysis methods based on the time domain.

Real-time motion estimation based video steganography with preserved consistency and local optimality

AbstractThis paper introduces a novel steganographic technique for H.264 video that achieves an outstanding performance against state-of-the-art steganalysis techniques while maintaining real-time encoding performance constraints. The proposed technique embeds the secret message by altering the motion vectors (MVs) while preserving their local optimality and consistency feature to withstand the recently emerged steganalysis methods. Thanks to its macro-block (MB) basis architecture, the proposed technique satisfies the real-time constraints, eliminating the need to wait for the whole frame or group of pictures (GOP) and avoiding the need to perform any additional re-encoding step(s). Additionally, altering the MVs is performed in the motion estimation (ME) sub-pixel-refinement stage through a rule-based scheme that ensures each MB’s compatibility for embedding without detection by the aforementioned steganalysis methods. The proposed technique is integrated with the OpenH264 real-time video encoder and evaluated on widely used video sequences. The results prove that the proposed technique achieves a significant security performance against the steganalysis methods while maintaining an acceptable embedding rate, outperforming other state-of-the-art MV-based steganographic methods in real-time constrained environments. The proposed technique adds about $$1-2\%$$ 1 - 2 % overhead beyond the encoder running time. The source code is publicly available here: https://github.com/HassanMohamedGit/OpenH264-RealTime-steg.

Embedded Feature Selection Approach Using Penalized Logistic Regression for Universal Steganalysis

For universal steganalysis, the Spatial Rich Model (SRM) provides a robust feature set in the form of 106 feature submodels (34671-dimensional) to attack highly secure steganography methods. Nonetheless, the curse of dimensionality emerges as a drawback, prompting researchers to explore feature selection methods to achieve optimal performance for steganalyzers. In previous work, a wrapper feature selection method using global and local best particle swarm optimization (GLBPSO) has been used to select 28 submodels of SRM out of 106 submodels. The 28 submodels contain a total of 9152 features and an ensemble classifier has been used for the classification results. In this study, an embedded feature selection and classification approach using logistic regression (LR) with an elastic net penalty has been proposed and applied to the 9152 features. The proposed approach efficiently selects an informative subset of 9152 features while training the LR classifier. This not only reduces the number of features by a significant 75% but also boosts the classification performance when contrasted with the ensemble classifier. The proposed approach achieves an accuracy of 87.41%, surpassing the current state-of-the-art steganalysis methods based on deep learning by a substantial margin of 3-7%. It also outperforms a recent machine learning-based steganalysis method by 13%.

Pixel-block-based Steganalysis Method for Hidden Data Location in Digital Images

Pixel-block-based Steganalysis Method for Hidden Data Location in Digital Images

An anti-steganalysis adaptive steganography for HEVC video based on PU partition modes

Calibration-based steganalysis methods are a fatal threat to current HEVC steganography algorithms. The current steganography algorithms based on prediction unit (PU) still lack resistance to this type of steganalysis. The reason is that the improvements in HEVC codec provide more potential steganographic space as well as introduce more detectable distortion. Therefore, a HEVC video steganography method that has resistance to PU shift-based steganalysis is proposed in this paper. First, the PU shift phenomenon that exists in PU-based steganography is introduced. Then the existing calibration-based steganalysis method is enhanced. According to the encoding rules of HEVC, the distortion cost function according to the difference of rate distortion cost (RD cost) during recompression is designed, which aims to obtain better resistance to calibration-based steganalysis. Experimental results demonstrate that the steganography algorithm designed in this paper provides excellent resistance ability for calibration-based steganalysis.

A convolutional neural network to detect possible hidden data in spatial domain images

Hiding secret data in digital multimedia has been essential to protect the data. Nevertheless, attackers with a steganalysis technique may break them. Existing steganalysis methods have good results with conventional Machine Learning (ML) techniques; however, the introduction of Convolutional Neural Network (CNN), a deep learning paradigm, achieved better performance over the previously proposed ML-based techniques. Though the existing CNN-based approaches yield good results, they present performance issues in classification accuracy and stability in the network training phase. This research proposes a new method with a CNN architecture to improve the hidden data detection accuracy and the training phase stability in spatial domain images. The proposed method comprises three phases: pre-processing, feature extraction, and classification. Firstly, in the pre-processing phase, we use spatial rich model filters to enhance the noise within images altered by data hiding; secondly, in the feature extraction phase, we use two-dimensional depthwise separable convolutions to improve the signal-to-noise and regular convolutions to model local features; and finally, in the classification, we use multi-scale average pooling for local features aggregation and representability enhancement regardless of the input size variation, followed by three fully connected layers to form the final feature maps that we transform into class probabilities using the softmax function. The results identify an improvement in the accuracy of the considered recent scheme ranging between 4.6 and 10.2% with reduced training time up to 30.81%.

A Siamese Inverted Residuals Network Image Steganalysis Scheme based on Deep Learning

With the rapid proliferation of urbanization, massive data in social networks are collected and aggregated in real time, making it possible for criminals to use images as a cover to spread secret information on the Internet. How to determine whether these images contain secret information is a huge challenge for multimedia computing security. The steganalysis method based on deep learning can effectively judge whether the pictures transmitted on the Internet in urban scenes contain secret information, which is of great significance to safeguarding national and social security. Image steganalysis based on deep learning has powerful learning ability and classification ability, and its detection accuracy of steganography images has surpassed that of traditional steganalysis based on manual feature extraction. In recent years, it has become a hot topic of the information hiding technology. However, the detection accuracy of existing deep learning based steganalysis methods still needs to be improved, especially when detecting arbitrary-size and multi-source images, their detection efficientness is easily affected by cover mismatch. In this manuscript, we propose a steganalysis method based on Inverse Residuals structured Siamese network (abbreviated as SiaIRNet method, Sia mese- I nverted- R esiduals- Net work Based method). The SiaIRNet method uses a siamese convolutional neural network (CNN) to obtain the residual features of subgraphs, including three stages of preprocessing, feature extraction, and classification. Firstly, a preprocessing layer with high-pass filters combined with depth-wise separable convolution is designed to more accurately capture the correlation of residuals between feature channels, which can help capture rich and effective residual features. Then, a feature extraction layer based on the Inverse Residuals structure is proposed, which improves the ability of the model to obtain residual features by expanding channels and reusing features. Finally, a fully connected layer is used to classify the cover image and the stego image features. Utilizing three general datasets, BossBase-1.01, BOWS2, and ALASKA#2, as cover images, a large number of experiments are conducted comparing with the state-of-the-art steganalysis methods. The experimental results show that compared with the classical SID method and the latest SiaStegNet method, the detection accuracy of the proposed method for 15 arbitrary-size images is improved by 15.96% and 5.86% on average, respectively, which verifies the higher detection accuracy and better adaptability of the proposed method to multi-source and arbitrary-size images in urban scenes.

Image steganalysis method based on cover selection and adaptive filtered residual network

Image steganalysis aims to detect secret messages embedded in digital images. Nowadays, deep learning-based image steganalysis methods have achieved promising detection performance. However, few existing deep learning-based steganalysis methods take cover selection into consideration. While some networks only utilize fixed filter kernels, which make little use of the learning ability of the network. To alleviate the issue, we propose an image steganalysis method based on cover selection and adaptive filtered residual networks (CSRNet), which can be used for stego images classification. Firstly, we devise a cover selection method, which is specifically divided into two parts. One part is a gray-level co-generation matrix-based (GLCM) multi-scale texture complexity measure to quantify texture complexity. And the other is an inverse power law function-based (IPLF) learning curve, which can contribute to determining the number of selected cover images. Secondly, we design a deep learning steganalysis network based on adaptive filtered kernel and residual learning, which employs the cover-selected images for training, and utilizes the network powerful classification ability. Finally, based on BOSSbase 1.01 and BOWS2, the experimental results show that compared with the classical and state-of-the-art steganalysis methods, the proposed method can not only significantly improve the detection accuracy, but also reduce time-space cost.

FedSpy: A Secure Collaborative Speech Steganalysis Framework Based on Federated Learning

Deep learning brings the opportunity to achieve effective speech steganalysis in speech signals. However, the speech samples used to train speech steganalysis models (i.e., steganalyzers) are usually sensitive and distributed among different agencies, making it impractical to train an effective centralized steganalyzer. Therefore, in this paper, we present an effective framework, named FedSpy, using federated learning, which enables multiple agencies to securely and jointly train the speech steganalysis models without sharing their speech samples. FedSpy is a flexible and extensible framework that can work effectively in conjunction with various deep-learning-based speech steganalysis methods. We evaluate the performance of FedSpy by detecting the most widely used Quantization Index Modulation-based speech steganography with three state-of-the-art deep-learning-based steganalysis methods representatively. The results show that FedSpy significantly outperforms the local steganalyzers and achieves good detection accuracy comparable to the centralized steganalyzer.