Assessment of Steganalytic Methods Using Multiple Regression Models

Böhme, Rainer

doi:10.1007/11558859_21

Cited by 32 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ref. 10 it was proposed that the compound error (within-and between-image errors not separated) could be modelled by a Cauchy distribution. Our observations indicate that the between-image error is not quite as heavily tailed as the Cauchy distribution (where the cumulative density F satisfies 1 − F (x) ∼ x −1 ) but has a tail index closer to 2 (i.e.…”

Section: Shape Of Between-image Errormentioning

confidence: 99%

“…Similar efforts have been made in a recent workshop paper, 10 where the accuracy of two quantitative attacks has been evaluated by means of generalised non-linear regression models. This work goes beyond the previous research in three respects: first, we show that the overall error distribution, which was previously assumed to be Cauchy, should actually be described as a compound distribution with at least two parts.…”

Section: Introduction and Modelmentioning

confidence: 95%

See 1 more Smart Citation

A two-factor error model for quantitative steganalysis

Böhme

Ker

2006

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Quantitative steganalysis refers to the exercise not only of detecting the presence of hidden stego messages in carrier objects, but also of estimating the secret message length. This problem is well studied, with many detectors proposed but only a sparse analysis of errors in the estimators. A deep understanding of the error model, however, is a fundamental requirement for the assessment and comparison of different detection methods. This paper presents a rationale for a two-factor model for sources of error in quantitative steganalysis, and shows evidence from a dedicated large-scale nested experimental set-up with a total of more than 200 million attacks. Apart from general findings about the distribution functions found in both classes of errors, their respective weight is determined, and implications for statistical hypothesis tests in benchmarking scenarios or regression analyses are demonstrated. The results are based on a rigorous comparison of five different detection methods under many different external conditions, such as size of the carrier, previous JPEG compression, and colour channel selection. We include analyses demonstrating the effects of local variance and cover saturation on the different sources of error, as well as presenting the case for a relative bias model for between-image error.

show abstract

Section: Shape Of Between-image Errormentioning

confidence: 99%

Section: Introduction and Modelmentioning

confidence: 95%

A two-factor error model for quantitative steganalysis

Böhme

Ker

2006

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, Böhme in [3] also found that images with noisy texture yield the least accurate stego detection. Related to those results, in our experiment, while having the same quality factor and using the same steganography technique, it has been shown that images captured using high resolution devices (Canon) are more distinguishable than cover and stego image from a low resolution device (Sony).…”

Section: Discussionmentioning

confidence: 96%

“…All images were crop to the center, resulting in image sizes of 640x480 pixels and saved in JPEG image format with quality factor of 75. This can help to ensure that the image dimensions is not correlated with spatial characteristics, such as noise or local energy as what mentioned in [3].…”

Section: Detection Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

On the Performance of Wavelet Decomposition Steganalysis with JSteg Steganography

Wahab

Briffa

Schaathun

2009

Digital Watermarking

View full text Add to dashboard Cite

Abstract. In this paper, we study the wavelet decomposition based steganalysis technique due to Lyu and Farid. Specifically we focus on its performance with JSteg steganograpy. It has been claimed that the LyuFarid technique can defeat JSteg; we confirm this using different images for the training and test sets of the SVM classifier. We also show that the technique heavily depends on the characteristics of training and test set. This is a problem for real-world implementation since the image source cannot necessarily be determined. With a wide range of image sources, training the classifier becomes problematic. By focusing only on different camera makes we show that steganalysis performances significantly less effective for cover images from certain sources.

show abstract

Bibliography

2012

Machine Learning in Image Steganalysis

View full text Add to dashboard Cite

Assessment of Steganalytic Methods Using Multiple Regression Models

Cited by 32 publications

References 20 publications

A two-factor error model for quantitative steganalysis

A two-factor error model for quantitative steganalysis

On the Performance of Wavelet Decomposition Steganalysis with JSteg Steganography

Bibliography

Contact Info

Product

Resources

About