Moving steganography and steganalysis from the laboratory into the real world

Abstract-The HUGO project, published at 2010, can be considered as one of the most promising direction in the design of highly undetectable steganography. The main idea of that approach is to minimise the embedding impact from the steganalysis point of view. This goal is achieved by using trellis codes in the embedding procedure, the Viterbi algorithm (VA) and the SPAM features. But the optimality of VA was kept still unclear because a generic purpose of VA is to correct errors with trellis codes instead of embedding secret information. The first goal of the current paper is to prove the optimality of VA application in its generalised form proposed about 30 years ago by one of the authors of this paper. The second goal is to optimise the parameters of the trellis code check matrix for better undetectability of stegosystems.

show abstract

“…We agree with the importance given to "Open Problem 1" in [7], namely the design of effective coding schemes for nonadditive distortion function.…”

Section: Discussionsupporting

confidence: 83%

Using the Generalised Viterbi Algorithm to Achieve a Highly Effective Stegosystem for Images

Korzhik¹,

Morales‐Luna²,

Fedyanin³

2015

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…Over the last ten years, most of the steganalysis methods are dealing with grayscale images [14], there exist very few steganalysis methods dealing with color images. The most recent methods in color image steganalysis are explained in detail in the three following subsections.…”

Section: Color Steganalysis Methodsmentioning

confidence: 99%

Color Image Steganalysis Based On Steerable Gaussian Filters Bank

Abdulrahman

Chaumont

Montesinos

et al. 2016

Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security

View full text Add to dashboard Cite

This article deals with color images steganalysis based on machine learning. The proposed approach enriches the features from the Color Rich Model by adding new features obtained by applying steerable Gaussian filters and then computing the co-occurrence of pixel pairs. Adding these new features to those obtained from Color-Rich Models allows us to increase the detectability of hidden messages in color images. The Gaussian filters are angled in different directions to precisely compute the tangent of the gradient vector. Then, the gradient magnitude and the derivative of this tangent direction are estimated. This refined method of estimation enables us to unearth the minor changes that have occurred in the image when a message is embedded. The efficiency of the proposed framework is demonstrated on three stenographic algorithms designed to hide messages in images: S-UNIWARD, WOW, and Synch-HILL. Each algorithm is tested using different payload sizes. The proposed approach is compared to three color image steganalysis methods based on computation features and Ensemble Classifier classification: the Spatial Color Rich Model, the CFA-aware Rich Model and the RGB Geometric Color Rich Model.

show abstract

“…This can be explained by the fact that all features in the CC-JRM are referencing each other and thus both CC-JRM and CC-JRM-pairs cases are quantitatively similar. .4446 ± .0145 CD-JRM (11,255) .2083 ± .0035 .3462 ± .0055 .2776 ± .0058 .2091 ± .0023 .2118 ± .0061 Table 7. Detection error for three versions of the JRM: CC-JRM, CC-JRM with random subspaces selected in pairs feature-reference (CC-JRM-pairs), and the difference calibrated JRM (CD-JRM).…”

Section: Experiments With the Cc-jrm Feature Vectormentioning

confidence: 99%

“…Given the great diversity and the associated complexity of the problem, it is not surprising that, at present, the problem of the CSM is rather poorly understood. It has also been identified as one of the main obstacles when deploying steganalysis in real world [11].…”

Section: Introductionmentioning

confidence: 99%

Study of cover source mismatch in steganalysis and ways to mitigate its impact

2014

Self Cite

View full text Add to dashboard Cite

When a steganalysis detector trained on one cover source is applied to images from a different source, generally the detection error increases due to the mismatch between both sources. In steganography, this situation is recognized as the so-called cover source mismatch (CSM). The drop in detection accuracy depends on many factors, including the properties of both sources, the detector construction, the feature space used to represent the covers, and the steganographic algorithm. Although well recognized as the single most important factor negatively affecting the performance of steganalyzers in practice, the CSM received surprisingly little attention from researchers. One of the reasons for this is the diversity with which the CSM can manifest. On a series of experiments in the spatial and JPEG domains, we refute some of the common misconceptions that the severity of the CSM is tied to the feature dimensionality or their "fragility." The CSM impact on detection appears too difficult to predict due to the effect of complex dependencies among the features. We also investigate ways to mitigate the negative effect of the CSM using simple measures, such as by enlarging the diversity of the training set (training on a mixture of sources) and by employing a bank of detectors trained on multiple different sources and testing on a detector trained on the closest source.

show abstract

Moving steganography and steganalysis from the laboratory into the real world

Cited by 216 publications

References 94 publications

Using the Generalised Viterbi Algorithm to Achieve a Highly Effective Stegosystem for Images

Using the Generalised Viterbi Algorithm to Achieve a Highly Effective Stegosystem for Images

Color Image Steganalysis Based On Steerable Gaussian Filters Bank

Study of cover source mismatch in steganalysis and ways to mitigate its impact

Contact Info

Product

Resources

About