Video steganography: A review

In the past few years, the Generative Adversarial Network (GAN), which proposed in 2014, has achieved great success. There have been increasing research achievements based on GAN in the field of computer vision and natural language processing. Image steganography is an information security technique aiming at hiding secret messages in common digital images for covert communication. Recently, research on image steganography has demonstrated great potential by introducing GAN and other neural network techniques. In this paper, we review the art of steganography with GANs according to the different strategies in data hiding, which are cover modification, cover selection, and cover synthesis. We discuss the characteristics of the three strategies of GAN-based steganography and analyze their evaluation metrics. Finally, some existing problems of image steganography with GAN are summarized and discussed. Potential future research topics are also forecasted.

Recent Advances of Image Steganography with Generative Adversarial Networks

The model mismatch problem occurs in steganalysis when a binary classifier is trained on objects from one cover source and tested on another: an example of domain adaptation. It is highly realistic because a steganalyst would rarely have access to much or any training data from their opponent, and its consequences can be devastating to classifier accuracy. This paper presents an in-depth study of one particular instance of model mismatch, in a set of images from Flickr using one fixed steganography and steganalysis method, attempting to separate different effects of mismatch in feature space and find methods of mitigation where possible. We also propose new benchmarks for accuracy, which are more appropriate than mean error rates when there are multiple actors and multiple images, and consider the case of 3-valued detectors which also output `don't know'. This pilot study demonstrates that some simple feature-centering and ensemble methods can reduce the mismatch penalty considerably, but not completely remove it.

/pdf/a-mishmash-of-methods-for-mitigating-the-model-mismatch-mess-kwmeeiltvc.pdf

A mishmash of methods for mitigating the model mismatch mess

The Internet is constantly growing in size and becoming more complex. The field of networking is thus continuously progressing to cope with this monumental growth of network traffic. While approaches such as Software Defined Networking (SDN) can provide a centralized control mechanism for network traffic measurement, control, and prediction, still the amount of data received by the SDN controller is huge. To process that data, it has recently been suggested to use Machine Learning (ML). In this paper, we review existing proposal for using ML in an SDN context for traffic measurement (specifically, classification) and traffic prediction. We will especially focus on approaches that use Deep learning (DL) in traffic prediction, which seems to have been mostly untapped by existing surveys. Furthermore, we discuss remaining challenges and suggest future research directions.

Machine Learning and Deep Learning Based Traffic Classification and Prediction in Software Defined Networking

In this paper we propose a novel framework for action recognition based on multiple features for improve action recognition in videos. The fusion of multiple features is important for recognizing actions as often a single feature based representation is not enough to capture the imaging variations (view-point, illumination etc.) and attributes of individuals (size, age, gender etc.). Hence, we use two kinds of features: i) a quantized vocabulary of local spatio-temporal (ST) volumes (cuboids and 2-D SIFT), and ii) the higher-order statistical models of interest points, which aims to capture the global information of the actor. We construct video representation in terms of local space-time features and global features and integrate such representations with hyper-sphere multi-class SVM. Experiments on publicly available datasets show that our proposed approach is effective. An additional experiment shows that using both local and global features provides a richer representation of human action when compared to the use of a single feature type.

Action Recognition by Multiple Features and Hyper-Sphere Multi-class SVM

Multi-class classification is an important and on-going research subject in machine learning and data mining. In this paper, we propose a new support vector algorithm, called OC-K-SVM, for multi-class classification based on one-class SVM. For k-class problem, this method constructs k classifiers, where each one is trained on data from one class. OC-K-SVM has parameters that enable us to control the number of support vectors and margin errors effectively, which is helpful in improving the accuracy of each classifier. We give some theoretical results concerning the significance of the parameters and show the robustness of classifiers. In addition, we have examined the proposed algorithm on several benchmark data sets, and our preliminary experiments confirm our theoretical conclusions.

/pdf/a-new-multi-class-svm-algorithm-based-on-one-class-svm-22desy9m89.pdf

A New Multi-class SVM Algorithm Based on One-Class SVM

With the development of Generative Adversarial Networks (GAN), GAN-based steganography and steganalysis techniques have attracted much attention from researchers. In this paper, we propose a novel image steganography method without modification based on Wasserstein GAN Gradient Penalty (WGAN-GP). The proposed architecture has a generative network, a discriminative network, and an extractor network. The Generator is used to generate the cover image (also is the stego image), and the Extractor is used to extract secret information. During the process of stego image generation, no modification operations are required. To make full use of the learning ability of convolutional neural networks and GAN, we synchronized the training of Generator and Extractor. Experiment results show that the proposed method has the advantages of higher recovery accuracy and higher training efficiency.

A Generative Steganography Method Based on WGAN-GP

The invention discloses a steganalysis algorithm specific to H.264 video motion vector information embedment. The algorithm aims at rapidly and effectively carrying out steganalysis to an H.264 video, and especially has relatively high detection rate specific to an embedding algorithm which keeps statistic characteristics unchanged and a low embedding rate relatively well. The technical scheme used by the invention is that motion vectors are accurately extracted; high order differential characteristics are designed on the basis of first order differential characteristics; according to this kind of characteristics, steganalysis can be carried out relatively well on a steganography algorithm which compensates vector statistic characteristics; multiple simple classifiers are trained by using integrated learning thought; an integrated steganography classifier based on FLD is designed; and the integrated classifier is relatively greatly improved in classification speed; and compared with single same classifiers, the integrated classifier has higher classification accuracy.

Steganalysis algorithm specific to H.264 video motion vector information embedment

Accompany with the growth of the speed in network, people's living standard has greatly improved, but the threaten to its information's security has also appeared, as a important branch of information security, steganography is a useful method to protect the secret information safety. In view of the high complexity of current video steganographic algorithms, and combining with the trailing coefficient produced in the process of quantization of H.264 encoding standard, we put forward a kind of algorithm based on trailing coefficients. The algorithm firstly conducts DCT transform on the frame, and then obtains the trailing coefficient for each quantized DCT blocks, last embedded by changing its values. The experimental result indicates that, this algorithm has little influence on video quality and has a few changes to the DCT coefficients after embedding, and has large capacity of steganography, and has high robustness. Above all, the information security has been protected.

Video Steganography Algorithm Based on Trailing Coefficients

On the basis of analyzing some existing video steganographic algorithms and find out some problems, like have large impact on the video quality and bit rate, so we propose a new algorithm based on grey relational analysis combining with the partition modes features of the H.264/AVC. The algorithm firstly compute the grey relevancy of blocks and judge if it has texture features. Then perform DCT on the current frame. Finally choose the proper capacity based on partition modes and embed information in DCT numbers. The experimental results show that the proposed algorithm has little impact on the video quality and bit rate, also has the advantages that anti-noise, anti-filter and high capacity information hiding.

Ke Niu

Papers

A New Multi-class SVM Algorithm Based on One-Class SVM

A Generative Steganography Method Based on WGAN-GP

Steganalysis algorithm specific to H.264 video motion vector information embedment

Video Steganography Algorithm Based on Trailing Coefficients

A Novel Information Hiding Algorithm Based on Grey Relational Analysis for H.264/AVC