Steganalysis by Subtractive Pixel Adjacency Matrix

Abstract

This paper presents a novel method for detection of steganographic methods that embed in the spatial domain by adding a low-amplitude independent stego signal, an example of which is LSB matching. First, arguments are provided for modeling differences between adjacent pixels using first-order and second-order Markov chains. Subsets of sample transition probability matrices are then used as features for a steganalyzer implemented by support vector machines. The accuracy of the presented steganalyzer is evaluated on LSB matching and four different databases. The steganalyzer achieves superior accuracy with respect to prior art and provides stable results across various cover sources. Since the feature set based on second-order Markov chain is highdimensional, we address the issue of curse of dimensionality using a feature selection algorithm and show that the curse did not occur in our experiments.

Steganalysis of Content-Adaptive Steganography in Spatial Domain

“…What is really needed for steganalysis is an unbiased estimate of the central pixel obtained from the neighboring pixels, excluding the pixel being estimated. The recently proposed SPAM feature set [13], as well as the earlier work [2,15], use the value of the neighboring pixel as the prediction:…”

“…To reduce its dimensionality, features are usually constructed as some integral quantities. Considering the noise residual as a Markov chain, one can take its sample transition probability matrix [2,13,15] or the sample joint probability matrix (the co-occurrence matrix) as a feature. To capture higher-order dependencies among pixels, higher-order co-occurrence matrices are usually formed.…”

“…The matrices for the horizontal and vertical directions (and diagonal and minor diagonal directions) are added together to decrease dimensionality and provide a more stable statistic. The following two feature types can be thought of as sums of joint distributions of consecutive residuals modeled as Markov chains in each direction (they are similar in spirit to the SPAM feature set [13]), while the next one is computed from the Ker-Böhme residual (4).…”

A Survey of Recent Embedding Techniques and Security Measures in Steganography

“…There are many methods available like MSE calculation, Subtractive Pixel Adjacency Matrix(SPAM) proposed by Pevny et al [ 10] and HVDH scheme proposed by Zhao et al [11]. The MSE calculation method fails in the case of LSB Matching techniques with low MSE also, is easily detectable.…”

Double Phase Modular Steganography Using Error Images of Lossy Wavelet Transforms

“…The best embedding order starts from pixels with the highest to lowest cost of embedding, which is ascertained by an additive distortion measure. Security is evaluated by training SVM (support vector machine)-based steganalyzers using second-order subtractive pixel adjacency model (SPAM) features [7]. A filter suppresses the stego image content and exposes the added noise in the stego image.…”