Dissemin is shutting down on January 1st, 2025

Links

Tools

Export citation

Search in Google Scholar

A Learning-Based Steganalytic Method against LSB Matching Steganography

Journal article published in 2011 by Zhihua Xia ORCID, Lincong Yang, Xingming Sun, Wei Liang, Decai Sun, Zhiqiang Ruan
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Question mark in circle
Preprint: policy unknown
Question mark in circle
Postprint: policy unknown
Question mark in circle
Published version: policy unknown

Abstract

This paper considers the detection of spatial domain least significant bit (LSB) matching steganography in gray images. Natural images hold some inherent properties, such as histogram, dependence between neighboring pixels, and dependence among pixels that are not adjacent to each other. These properties are likely to be disturbed by LSB matching. Firstly, histogram will become smoother after LSB matching. Secondly, the two kinds of dependence will be weakened by the message embedding. Accordingly, three features, which are respec-tively based on image histogram, neighborhood degree histogram and run-length histogram, are extracted at first. Then, support vector machine is utilized to learn and dis-criminate the difference of features between cover and stego images. Experimental results prove that the proposed method possesses reliable detection ability and outperforms the two previous state-of-the-art methods. Further more, the conclusions are drawn by analyzing the individual performance of three features and their fused feature.