Cover Source Mismatch Research Articles

Cover-source mismatch in steganalysis: systematic review

Operational steganalysis contends with a major problem referred to as the cover-source mismatch (CSM), which is essentially a difference in distribution caused by different parameters and settings over training and test data. Despite it being of fundamental importance in an operational context, the CSM problem is often overlooked in the literature. With the goal to increase the visibility of this problem and attract the interest of the community, the present paper proposes a systematic review of the literature. It summarizes gathered knowledge and major open questions over the last 20 years of active research on CSM: terminology, methods of measurement, known causes, and mitigation strategies. Over 100 papers exploring, mitigating, assessing, or discussing steganalysis under train-test mismatch were collected by sampling scholar databases, and tracing references, cited and generated. For image steganalysis, the literature provided enough evidence to quantify the impact of causes, and the effectiveness of mitigation strategies.

RCDD: Contrastive domain discrepancy with reliable steganalysis labeling for cover source mismatch

The cover source mismatch (CSM) can be very challenging for steganalysis because different distribution between source and target inevitably leads to poor performance of the steganalyzer on the target domain. In general, some methods from unsupervised domain adaptation, such as contrastive domain discrepancy (CDD), can be directly applied to steganalysis for addressing the CSM problem, but they cannot achieve satisfactory detection accuracy due to the neglect of steganographic characteristics. To solve this problem, reliable steganalysis labeling (RSL)-based CDD (RCDD) taking steganographic characteristics in account is proposed in this paper, which relies on RSL to generate reliable labels for extended target images, rather than utilizing clustering in CDD to obtain unreliable pseudo labels for target images. Through detailed deduction process, we know that RCDD draws closer the distribution of source and target classwisely so as to enhance the classification performance on the target domain. Simultaneously, a corresponding steganalysis network RCDD-Net is yielded by incorporating some backbone into RCDD. A large number of experiments verify that RCDD-Net is an innovation in steganalysis that effectively alleviates performance degradation when CSM occurs. Moreover, RCDD-Net provides better detection performance than several advanced steganalysis networks.

Tackling the Cover Source Mismatch Problem in Audio Steganalysis With Unsupervised Domain Adaptation

Nowadays, the convolutional neural network (CNN) based steganalysis has achieved remarkable performance in the well-controlled lab environment. However, the cover source mismatch (CSM) problem, which can be attributed to the discrepancy between the training, and evaluation datasets, is still one of the pivotal obstacles for adapting the steganalysis into real-world applications. In this letter, we propose to merge the domain adaptation strategy into CNN-based audio steganalysis for handling the CSM problem. Specifically, the proposed framework contains three components: feature extractor, steganalytic classifier, and domain discriminator. The cascade of feature extractor, and steganalytic classifier compose the typical supervised steganalysis model. The unsupervised domain adaptation is implemented by the domain adversarial training between the feature extractor, and domain discriminator. Ultimately, the feature extractor is trained to extract the steganalytic, and domain-invariant features. It aims to reduce the domain gap between the training data, and testing data. The experimental results show that our approach could effectively mitigate the CSM impact caused by the diversity of audio recording devices.

Effects and solutions of Cover-Source Mismatch in image steganalysis

The Cover-Source Mismatch (CSM) has been long recognized as a major problem in modern steganography and steganalysis. Indeed, while a vast majority of works in steganography and steganalysis had been tailored to a specific reference database, namely BOSSbase, recent works show that, because of CSM, the results may greatly differ when changing this dataset. Although the CSM has already been the subject of several publications, these prior works investigated only a few elements in a limited setup. The goal of the current paper is to study the effects of the CSM in a more comprehensive manner and then to examine and compare different strategies for mitigating it. It first defines two different parameters, the source difficulty and the source inconsistency, which are involved in the CSM. Then, using different steganographic schemes and feature sets, it aims at providing a systematic study regarding the various factors that can give birth to CSM for image steganalysis. Finally, two practical ways to mitigate the CSM, using training techniques promoting either diversity of different sources or the specificity of one targeted source which is beforehand identified by training a multi-class classifier, are presented and their performances are compared for different training set sizes.

Steganalysis on Internet images via domain adaptive classifier

In recent years, various steganalysis algorithms have been proposed and achieved satisfactory performance. However, these conventional methods are not effective for mismatched steganalysis. In real world, there are millions of images captured by different cameras and users transmitted on the Internet every day. The steganalysis on Internet images will encounter steganographic algorithm mismatch (SAM) and cover source mismatch (CSM). Therefore, the steganalysis on the Internet is essentially to solve the mismatch problem. This paper proposes a method to solve the mismatched steganalysis on the Internet images by domain adaptation classifier. It makes the distribution between training and testing sets more similar to obtain better detection performance. We integrate joint distribution adaptation and geometric structure as regularization terms to a standard supervised classifier. Specifically, joint distribution adaptation contains marginal and conditional distributions. And considering the characteristics of steganalysis on the Internet images, we add the conditional regularization in the geometric structure to the existing algorithms. Experimental results (include SAM and CSM) on Internet images show that our method has a better performance than state-of-the-art methods.

Selection of Robust and Relevant Features for 3-D Steganalysis.

While 3-D steganography and digital watermarking represent methods for embedding information into 3-D objects, 3-D steganalysis aims to find the hidden information. Previous research studies have shown that by estimating the parameters modeling the statistics of 3-D features and feeding them into a classifier we can identify whether a 3-D object carries secret information. For training the steganalyzer, such features are extracted from cover and stego pairs, representing the original 3-D objects and those carrying hidden information. However, in practical applications, the steganalyzer would have to distinguish stego-objects from cover-objects, which most likely have not been used during the training. This represents a significant challenge for existing steganalyzers, raising a challenge known as the cover source mismatch (CSM) problem, which is due to the significant limitation of their generalization ability. This paper proposes a novel feature selection algorithm taking into account both feature robustness and relevance in order to mitigate the CSM problem in 3-D steganalysis. In the context of the proposed methodology, new shapes are generated by distorting those used in the training. Then a subset of features is selected from a larger given set, by assessing their effectiveness in separating cover-objects from stego-objects among the generated sets of objects. Two different measures are used for selecting the appropriate features: 1) the Pearson correlation coefficient and 2) the mutual information criterion.

Study on the interaction between the cover source mismatch and texture complexity in steganalysis

Cover source mismatch (CSM) occurs when a detection classifier for steganalysis trained on objects from one cover source is tested on another source. However, it is very hard to find the same sources as suspicious images in real-world applications. Therefore, the CSM is one of the biggest stumbling blocks to hinder current classifier based steganalysis methods from becoming practical. Meanwhile, the texture complexity (of digital images) also plays an important role in affecting the detection accuracy of steganalysis. Previous work seldom conduct research on the interaction between the two factors of the CSM and the texture complexity (TC). This paper studies the interaction between the two factors and explore certain factor related to cover source mismatch, aiming to improve the steganalysis accuracy in the case of CSM. We propose an effective method to measure the TC via image filtering, and use the two-way analysis of variance to study the interaction between the two factors. Both non-adaptive and adaptive steganography experiments are carried out with different levels of TC and CSM. The experimental results have shown that the interaction between the two factors affects the detection accuracy significantly.

Steganalysis into the Wild: How to Define a Source?

It is now well known that practical steganalysis using machine learning techniques can be strongly biased by the problem of Cover Source Mismatch. Such a phenomenon usually occurs in machine learning when the and the testing sets are drawn from different sources, i.e. when they do not share the same statistical properties. In the field of steganalysis however, due to the small power of the signal targeted by steganalysis methods, it can drastically lower their performance. This paper aims to define through practical experiments what is a source in steganalysis. By assuming that two cover datasets coming from a common source should provide comparable performances in steganalysis, it is shown that the definition of a source is more related with the processing pipeline of the RAW images than with the sensor or the acquisition setup of the pictures. In order to measure the discrepancy between sources, this paper introduces the concept of consistency between sources, that quantifies how much two sources are subject to Cover Source Mismatch. We show that by adopting training de-sign, we can increase the consistency between the set and the testing set. To measure how much image processing operation may help the steganographers this paper also introduces the intrinsic difficulty of a source. It is observed that some processes such as JPEG quan-tization tables or the development pipeline can dramatically increase or decrease the performance of steganalysis methods and that other parameters such as the ISO sensitivity or the sensor model have minor impact on the performance.

A Steganalytic Approach to Detect Motion Vector Modification Using Near-Perfect Estimation for Local Optimality

This paper presents a steganalytic approach against motion vector-based video steganography that does not depend on the detailed knowledge of embedding algorithms. In most state-of-the-art video coding standards, the motion vector is the result of block-based motion estimation using rate-distortion optimization. That is to say, each motion vector is locally optimal in a rate-distortion sense, and any modification will inevitably shift the motion vector from locally optimal to non-optimal. As a consequence, it is a very strong evidence of steganography if some motion vectors are found to be locally non-optimal. Based on this fact, the core of our method is an estimator to check the local optimality of motion vectors in a rate-distortion sense. We try to recover the necessary information used for motion vector decision that is lost during lossy compression, based on which a 36-D feature set is formed for training and classification. To demonstrate the effectiveness of the proposed approach, experiments are carried out in different settings. The corresponding results show that our approach has a wide applicability even at low embedding strengths. Particularly, the problem of cover source mismatch is largely alleviated, which indicates that the proposed approach is suitable to be used in situations where a very limited priori knowledge is available.

Segmentation Based Video Steganalysis to Detect Motion Vector Modification

This paper presents a steganalytic approach against video steganography which modifies motion vector (MV) in content adaptive manner. Current video steganalytic schemes extract features from fixed-length frames of the whole video and do not take advantage of the content diversity. Consequently, the effectiveness of the steganalytic feature is influenced by video content and the problem of cover source mismatch also affects the steganalytic performance. The goal of this paper is to propose a steganalytic method which can suppress the differences of statistical characteristics caused by video content. The given video is segmented to subsequences according to block’s motion in every frame. The steganalytic features extracted from each category of subsequences with close motion intensity are used to build one classifier. The final steganalytic result can be obtained by fusing the results of weighted classifiers. The experimental results have demonstrated that our method can effectively improve the performance of video steganalysis, especially for videos of low bitrate and low embedding ratio.

New Blind Steganalysis Framework Combining Image Retrieval and Outlier Detection

The detection accuracy of steganalysis depends on many factors, including the embedding algorithm, the payload size, the steganalysis feature space and the properties of the cover source. In practice, the cover source mismatch (CSM) problem has been recognized as the single most important factor negatively affecting the performance. To address this problem, we propose a new framework for blind, universal steganalysis which uses traditional steganalyst features. Firstly, cover images with the same statistical properties are searched from a reference image database as aided samples. The test image and its aided samples form a whole test set. Then, by assuming that most of the aided samples are innocent, we conduct outlier detection on the test set to judge the test image as cover or stego. In this way, the framework has removed the need for training. Hence, it does not suffer from cover source mismatch. Because it performs anomaly detection rather than classification, this method is totally unsupervised. The results in our study show that this framework works superior than one-class support vector machine and the outlier detector without considering the image retrieval process.

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover sourcemismatch

Since the BOSS competition, in 2010, most steganalysis approaches use a learning methodology involving two steps: feature extraction, such as the Rich Models (RM), for the image representation, and use of the Ensemble Classifier (EC) for the learning step. In 2015, Qian et al. have shown that the use of a deep learning approach that jointly learns and computes the features, was very promising for the steganalysis. In this paper, we follow-up the study of Qian et al., and show that in the scenario where the steganograph always uses the same embedding key for embedding with the simulator in the different images, due to intrinsic joint minimization and the preservation of spatial information, the results obtained from a Convolutional Neural Network (CNN) or a Fully Connected Neural Network (FNN), if well parameterized, surpass the conventional use of a RM with an EC. First, numerous experiments were conducted in order to find the best "shape" of the CNN. Second, experiments were carried out in the clairvoyant scenario in order to compare the CNN and FNN to an RM with an EC. The results show more than 16% reduction in the classification error with our CNN or FNN. Third, experiments were also performed in a cover-source mismatch setting. The results show that the CNN and FNN are naturally robust to the mismatch problem. In Addition to the experiments, we provide discussions on the internal mechanisms of a CNN, and weave links with some previously stated ideas, in order to understand the results we obtained. We also have a discussion on the scenario "same embedding key".

Unsupervised steganalysis based on artificial training sets

In this paper, an unsupervised steganalysis method that combines artificial training sets and supervised classification is proposed. We provide a formal framework for unsupervised classification of stego and cover images in the typical situation of targeted steganalysis (i.e., for a known algorithm and approximate embedding bit rate). We also present a complete set of experiments using (1) eight different image databases, (2) image features based on Rich Models, and (3) three different embedding algorithms: Least Significant Bit (LSB) matching, Highly undetectable steganography (HUGO) and Wavelet Obtained Weights (WOW). We show that the experimental results outperform previous methods based on Rich Models in the majority of the tested cases. At the same time, the proposed approach bypasses the problem of Cover Source Mismatch – when the embedding algorithm and bit rate are known – since it removes the need of a training database when we have a large enough testing set. Furthermore, we provide a generic proof of the proposed framework in the machine learning context. Hence, the results of this paper could be extended to other classification problems similar to steganalysis.