Chi-Square Detection for PVD Steganography
I-Hui Pan, Kung-Chin Liu, Chiang-Lung Liu
Abstract
Although the Pixel-Value Differencing (PVD) steganography can avoid being detected by the RS steganalysis, the histogram of the pixel-value differences poses an abnormal distribution. Based on this hiding characteristic, this paper proposes a PVD steganalysis based on chi-Square statistics. The degrees of freedom were adopted to be tested for obtaining various detection accuracies (ACs). Experimental results demonstrate the detection accuracies are all above 80%. When the degrees of freedom are set as 10 while the accuracy is the best (AC = 83%). It means that the proposed Chi-Square based method is an efficient detection for PVD steganography.
Topics & Concepts
SteganalysisSteganographyHistogramPixelComputer scienceLeast significant bitPattern recognition (psychology)Artificial intelligenceSquare (algebra)MathematicsImage (mathematics)GeometryOperating systemAdvanced Steganography and Watermarking TechniquesDigital Media Forensic DetectionChaos-based Image/Signal Encryption