Steganalysis Approach Research Articles

Independent Video Steganalysis Framework Perspective of Secure Video Processing

We have designed an algorithm of cross-domain feature set extraction for cross-domain video steganalysis of video steganography in multiple domains. For video steganography, we implemented the recently proposed steganography methods such as PMs, MVs, and IPMs. The outcomes of these techniques have fed as input to the proposed Steganalysis approach. We have designed a cross-domain technique for Steganalysis in which the global feature set is extracted according to common statistical properties. After the extraction of global features, the domain-specific features have been extracted in the local features set. Both global and local features are set to form the cross-domain steganalysis technique. The classification has been performed by using the conventional machine learning classifiers such as Support Vector Machine (SVM) and Artificial Neural Network (ANN).

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.

A generalized image steganalysis approach via decision level fusion of deep models

A generalized image steganalysis approach via decision level fusion of deep models

Steganalysis of adaptive multi-rate speech with unknown embedding rates using clustering and ensemble learning

With the widespread use of adaptive multi-rate (AMR) speech-based applications, AMR speech-based steganography has witnessed significant growth. Consequently, steganalysis approaches have garnered attention to mitigate network security risks associated with AMR speech-based steganography. However, existing studies often assume known embedding rates of test samples, leaving steganography detection under unknown embedding rates—an encountered practical scenario—unresolved. To tackle this challenge, this paper presents a novel detection scheme for AMR speech-based steganography, skillfully combining clustering and ensemble learning. The training phase utilizes K-means clustering to pre-classify speech samples, grouping them into distinct clusters based on their feature distribution and embedding rates. Subsequently, a classifier based on extreme gradient boosting (XGBoost) is trained for each cluster. The experimental results demonstrate that the proposed scheme exhibits significant improvements in terms of recall rate when compared to existing steganalysis techniques.

Towards improving the performance of blind image steganalyzer using third-order SPAM features and ensemble classifier

The success rate for blind or universal steganalysis lies in the ability to extract the statistical footprints of image features. Further, the choice of machine learning (ML) algorithm is crucial to distinguish the stego image more precisely from the untouched clean images. Literature suggests that most steganalysis approaches report less favorable detection accuracy despite considering many features. This study presents a three-step process to accurately identify the clean and stego images to solve this issue. We used the curvelet denoising as an initial phase during the first step to suppress the natural noise residuals (NRs) by producing the stego NRs. Secondly, it extracts the Third-order Markov-chain sample transition probability matrices as features. Finally, the oblique decision tree ensemble using a multisurface proximal support vector machine (SVM) classifier has been utilized to achieve greater detection accuracy than the state-of-the-art classifiers. The experiments are performed on an extensive database comprising clean and stego images generated from nine embedding schemes with varying payloads. The experimental results suggest that an accuracy of 93.12 has been achieved using the proposed Third order subtractive pixel adjacency matrix (SPAM) features with an ensemble classifier.

A New Approach for JPEG Steganalysis with a Cognitive Evolving Ensembler and Robust Feature Selection

A New Approach for JPEG Steganalysis with a Cognitive Evolving Ensembler and Robust Feature Selection

A General Linguistic Steganalysis Framework Using Multi-Task Learning

Prevailing linguistic steganalysis approaches focus on learning sensitive features to distinguish a particular category of steganographic texts from non-steganographic texts, by performing binary classification. While it remains an unsolved problem and poses a significant threat to the security of cyberspace when various categories of non-steganographic or steganographic texts coexist. In this paper, we propose a general linguistic steganalysis framework named LS-MTL, which introduces the idea of multi-task learning to deal with the classification of various categories of steganographic and non-steganographic texts. LS-MTL captures sensitive linguistic features from multiple related linguistic steganalysis tasks and can concurrently handle diverse tasks with a constructed model. In the proposed framework, convolutional neural networks (CNNs) are utilized as private base models to extract sensitive features for each steganalysis task. Besides, a shared CNN is built to capture potential interaction information and share linguistic features among all tasks. Finally, LS-MTL incorporates the private and shared sensitive features to identify the detected text as steganographic or non-steganographic. Experimental results demonstrate that the proposed framework LS-MTL outperforms the baseline in the multi-category linguistic steganalysis task, while average Acc, Pre, and Rec are increased by 0.5%, 1.4%, and 0.4%, respectively. More ablation experimental results show that LS-MTL with the shared module has robust generalization capability and achieves good detection performance even in the case of spare data.

A Deep Learning Driven Feature Based Steganalysis Approach

A Deep Learning Driven Feature Based Steganalysis Approach

GUI Implementation of Modified and Secure Image Steganography Using Least Significant Bit Substitution

Due to swift improvement of information innovation in recent times, providing security to data has become major concern and threat to Information Privacy has become inevitable. Data Hiding technology is an efficient way to solve the problems of data leakage and loss of information. Data hiding called steganography is a security method to provide security to secret data which is transferred from sender to receiver from harmful attacks. Steganography is an interaction of concealing a mysterious message inside a cover object which is not secret. There are many cover media like images, audio, video, text files etc. There are many ways to approach steganography like spatial domain, transformation domain, masking and filtering. This technique is helpful because the human eye is quite insensitive to the minute changes that help the embedded data stay safe and secure. The main motive of steganography is to get high stego image quality, low computational complexity, more embedding capability, visually unnoticeable, invisibility, and improved security. A capable steganographic technique must be resistant to any steganalysis approach the secret data is prone to. In this proposed system, implement the GUI implementation image steganography in spatial domain using Least Significant Bit (LSB) where the modified high capacity cover image undergoes the Discrete Wavelet Transformation (DWT) and propose an Advanced Encryption Standard (AES) secret key stego system such that the data is secure. The distortion between the two images in identified with the help of MSE and Histogram analysis.

Towards blind detection of steganography in low‐bit‐rate speech streams

To prevent the abuse of low-rate speech-based steganography from threatening cyberspace security, the corresponding steganalysis approaches have been developed and received significant attention from research community. However, most existing steganalysis methods assume that steganography methods are known in advance, which in practice is impractical. That is why, in this paper, we present three blind detection schemes suitable for steganography in low-bit-rate speech streams. The first is based on mixed sample data augmentation. It randomly selects a certain proportion of steganographic samples from the sample set of each steganographic method to form a training set together with the original carrier samples for training to enhance the robustness of the model. The second relies on decision fusion where first step is to train a dedicated classification model for each steganography method and then use a majority voting mechanism in the detection stage to fuse the outputs of each model to give the final detection result. Compared to the other two steganalysis schemes, the third one design the detection model based on self-paced ensemble according to the distribution characteristics of speech samples. Its main idea is to fully train multiple base classifiers through multiple iterations as well as under-sampling processes, and organically fuse them to form a powerful ensemble classifier. In each iteration, differing from the traditional ensemble classifier solution, we put more attention to the steganographic samples at the decision boundary for the under-sampling process of the steganography set composed of multiple steganography methods, rather than randomly selecting steganographic samples. The steganographic samples at the decision boundary are searched using the classification hardness given by the ensemble classifier trained in the last iteration, which is more informative and more conducive to improve the performance of base classifiers. The experimental results show that the proposed three schemes can achieve efficient blind detection for low-bit-rate speech-based steganography, and the steganalysis scheme based on the self-paced ensemble has the best performance. Specifically, when the embedding rate is at 30%, the accuracy of the steganalysis scheme based on self-paced ensemble is more than 85%, while the accuracy of the other two steganalysis method is less than 80%. Additionally, the steganalysis scheme based on the self-paced ensemble learning even outperforms dedicated detectors for specific steganographic methods in terms of recall for steganographic sample detection.

Comprehensive Survey of Multimedia Steganalysis: Techniques, Evaluations, and Trends in Future Research

During recent years, emerging multimedia processing techniques with information security services have received a lot of attention. Among those trends are steganography and steganalysis. Steganography techniques aim to hide the existence of secret messages in an innocent-looking medium, where the medium before and after embedding looks symmetric. Steganalysis techniques aim to breach steganography techniques and detect the presence of invisible messages. In the modern world, digital multimedia such as audio, images, and video became popular and widespread, which makes them perfect candidates for steganography. Monitoring this huge multimedia while the user communicates with the outside world is very important for detecting whether there is a hidden message in any suspicious communication. However, steganalysis has a significant role in many fields, such as to extract the stego-message, to detect suspicious hidden messages and to evaluate the robustness of existing steganography techniques. This survey provides the general principles of hiding secret messages using digital multimedia as well as reviewing the background of steganalysis. In this survey, the steganalysis is classified based on many points of view for better understanding. In addition, it provides a deep review and summarizes recent steganalysis approaches and techniques for audio, images, and video. Finally, the existing shortcomings and future recommendations in this field are discussed to present a useful resource for future research.

Efficient Steganography in JPEG Images by Minimizing Performance of Optimal Detector

Since the introduction of adaptive steganography, most of the recent research works seek at designing cost functions that are evaluated against steganalysis methods. While those approaches have been successful, they rely on intuitive principles and ad-hoc costs associated with each pixel or Discrete Cosine Transform (DCT) coefficient. Beyond the empirical assessments, the insights one can get from such approaches are very limited. On the opposite, this paper presents an original method for steganography in JPEG images that exploits a statistical model of the DCT coefficients. Within the framework of hypothesis testing theory, we use a statistical model of covers to derive the analytical expression of the most powerful detector. The objective of the steganographer is to minimize the statistical performance of this “omniscient detector” which represents a “worst-case” scenario for security. This paper shows how this method allows designing effective steganography, in terms of both security and computational complexity, in the two main use cases: when having only one single JPEG image and when the uncompressed image is available, case also known as Side-Informed (SI). A wide range of numerical comparisons shows that the proposed method outperforms the current state-of-the-art especially against the latest and most accurate steganalysis approaches based on Deep Learning.

Multimedia Concealed Data Detection Using Quantitative Steganalysis

In current days, there is a constant evolution in modern technology. The most predominant usage of technology by society is the internet. There are many ways and means on the internet through which data is transmitted. Having such rapid and fast growth of communicating media also increases the exposure to security threats, causing unintellectual information ingress. Steganography is the main aspect of communicating in an aspect that hides the extent of communication. Steganalysis is another essential concern in data concealing, which is the art of identifying the existence of steganography. A framework has been designed to identify the concealed data in the multimedia file in the proposed system. This work's main strength is analyzing concealed data images without embedding and extracting the image's payloads. A quantitative steganalysis approach was considered to accomplish the proposed objective. By using this approach, the results were achieved with 98% accuracy.

Steganographic Analysis of Blockchains.

Steganography is one of the ways to hide data between parties. Its use can be worrisome, e.g., to hide illegal communications. Researchers found that public blockchains can be an attractive place to hide communications; however, there is not much evidence of actual use in blockchains. Besides, previous work showed a lack of steganalysis methods for blockchains. In this context, we present a steganalysis approach for blockchains, evaluating it in Bitcoin and Ethereum, both popular cryptocurrencies. The main objective is to answer if one can find steganography in real case scenarios, focusing on LSB of addresses and nonces. Our sequential analysis included 253 GiB and 107 GiB of bitcoin and ethereum, respectively. We also analyzed up to 98 million bitcoin clusters. We found that bitcoin clusters could carry up to 360 KiB of hidden data if used for such a purpose. We have not found any concrete evidence of hidden data in the blockchains. The sequential analysis may not capture the perspective of the users of the blockchain network. In this case, we recommend clustering analysis, but it depends on the clustering method’s accuracy. Steganalysis is an essential aspect of blockchain security.

Neural Linguistic Steganalysis via Multi-Head Self-Attention

Linguistic steganalysis can indicate the existence of steganographic content in suspicious text carriers. Precise linguistic steganalysis on suspicious carrier is critical for multimedia security. In this paper, we introduced a neural linguistic steganalysis approach based on multi-head self-attention. In the proposed steganalysis approach, words in text are firstly mapped into semantic space with a hidden representation for better modeling the semantic features. Then, we utilize multi-head self-attention to model the interactions between words in carrier. Finally, a softmax layer is utilized to categorize the input text as cover or stego. Extensive experiments validate the effectiveness of our approach.

An HEVC steganalytic approach against motion vector modification using local optimality in candidate list

Abstract Current research of video steganalysis is mainly oriented to H.264 or even earlier formats. As the H.265/HEVC standard is becoming more and more popular, there have been steganographic methods specifically designed for HEVC videos. Previous steganalytic methods are no longer effective due to the new features of HEVC. The advanced motion vector prediction technique employed by HEVC provides a new way for motion vector (MV) modification, utilizing the index of the candidate MV list. Such modification cannot be detected by previous steganalytic methods because the value of MV is not changed. To solve this problem, we proposed a new steganalytic strategy employing not only the local optimality of MV but also the local optimality in the candidate list. Combining the two types of local optimality, a 40-dimensional feature set is designed. Extensive experiments are carried out to evaluate the effectiveness of the proposed feature set. It is shown that compared with three current steganalyzers, our approach improves the performance against typical MV modification methods under various settings. In particular, our approach significantly boosts the detection accuracy of the index modification method that is exclusive to HEVC videos. To our best knowledge, this is the first work of video steganalytic method exploiting the new features of HEVC format.

Blind MV-based video steganalysis based on joint inter-frame and intra-frame statistics

Despite all its irrefutable benefits, the development of steganography methods has sparked ever-increasing concerns over steganography abuse in recent decades. To prevent the inimical usage of steganography, steganalysis approaches have been introduced. Since motion vector manipulation leads to random and indirect changes in the statistics of videos, MV-based video steganography has been the center of attention in recent years. In this paper, we propose a 54-dimentional feature set exploiting spatio-temporal features of motion vectors to blindly detect MV-based stego videos. The idea behind the proposed features originates from two facts. First, there are strong dependencies among neighboring MVs due to utilizing rate-distortion optimization techniques and belonging to the same rigid object or static background. Accordingly, MV manipulation can leave important clues on the differences between each MV and the MVs belonging to the neighboring blocks. Second, a majority of MVs in original videos are locally optimal after decoding concerning the Lagrangian multiplier, notwithstanding the information loss during compression. Motion vector alteration during information embedding can affect these statistics that can be utilized for steganalysis. Experimental results have shown that our features’ performance far exceeds that of state-of-the-art steganalysis methods. This outstanding performance lies in the utilization of complementary spatio-temporal statistics affected by MV manipulation as well as feature dimensionality reduction applied to prevent overfitting. Moreover, unlike other existing MV-based steganalysis methods, our proposed features can be adjusted to various settings of the state-of-the-art video codec standards such as sub-pixel motion estimation and variable-block-size motion estimation.

Combined features for steganalysis against PU partition mode-based steganography in HEVC

Many innovation modules introduced by High Efficiency Video Coding (HEVC) are remaining unexplored in the steganography domain. In this paper, a novel steganalytic approach is proposed against the PU partition mode-based steganographic methods which makes use of some innovative features in HEVC. Firstly, the influence of multilevel information embedding on the group proportion and the group proportion difference before and after recompression is analyzed. Then the statistical distribution of these two aspects are modeled as two different feature sets, and these two feature sets are combined for the final feature design to generate a 24-dimensional classification feature. Finally, a feature optimization is applied to reduce the 24-dimensional steganalysis feature to a 6-dimensional feature. It is demonstrated in experiment results that the proposed features have achieved a more accurate detection rate than current steganalysis methods under various circumstances, especially in the low embedding level situation.

A Dilated Convolutional Neural Network as Feature Selector for Spatial Image Steganalysis – A Hybrid Classification Scheme

Nowadays, while steganography is the main mean of illegal secret communication, the need of detecting steganographic content and especially stego images is becoming more compulsory. Since multimedia content can be easily spread over the internet and more complicated steganography algorithms in different domains i.e. spatial, transform are utilized, the task of identifying stego images becomes very difficult. Early steganalysis methods deploy statistical attacks on stego images while more recent ones use deep learning techniques. The latter ones mainly utilize convolutional neural networks and show promising results. In this paper we propose a novel method to identify stego images derived from two different steganographic algorithms S-UNIWARD (Spatial-UNIversal WAvelet Relative Distortion) and WOW (Wavelet Obtained Weights) for various embedding rates. The proposed method initially utilizes a dilated convolutional neural network as a feature extractor and afterwards the extracted feature vector trains a random forest classifier. More specifically it is proved that in steganalysis, a dilated convolutional neural network could be an excellent feature extractor and the traditional softmax layer could be replaced by another machine learning classifier. Extensive experiments were conducted, and the proposed model was also compared against state-of the-art convolutional neural networks utilized in spatial image steganalysis, and other feature extraction methods. Results showed that the proposed method achieves high classification accuracy and outperforms other analogous steganalysis approaches.

FedSteg: A Federated Transfer Learning Framework for Secure Image Steganalysis

The protection of user private data has long been the focus of AI security. We know that training machine learning models rely on large amounts of user data. However, user data often exists in the form of isolated islands that can not be integrated under many secure and legal constraints. The large-scale application of image steganalysis algorithms in real life is still not satisfactory due to the following challenges. First, it is difficult to aggregate all of the scattered steganographic images to train a robust classifier. Second, even if the images are encrypted, participants do not want irrelevant people to peek into the hidden information, resulting in the disclosure of private data. Finally, it is often impossible for different participants to train their tailored models. In this paper, we introduce a novel framework, referred to as FedSteg, to train a secure, personalized distributed model through federated transfer learning to fulfill secure image steganalysis. Extensive experiments on detecting several state-of-the-art steganographic methods i.e., WOW, S-UNIWARD, and HILL, validate that FedSteg achieves certain improvements compared to traditional non-federated steganalysis approaches. In addition, FedSteg is highly extensible and can be easily employed to various large-scale secure steganographic recognition tasks.