WPD-based blind image steganalysis

LUO Xiang-yang1; LIU Fen-lin1; WANG Dao-shun2

您当前的位置：

首页 >

文章列表页 >

WPD-based blind image steganalysis

更新时间：2024-10-14

- WPD-based blind image steganalysis
- Issue 10, Pages: 173-182(2008)
- 作者机构：
  
  1. 解放军信息工程大学信息工程学院
  2. 清华大学计算机科学与技术系
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.41
- Published：2008
- 稿件说明：
移动端阅览
LUO Xiang-yang1, LIU Fen-lin1, WANG Dao-shun2. WPD-based blind image steganalysis[J]. 2008, (10): 173-182.
DOI：

LUO Xiang-yang1, LIU Fen-lin1, WANG Dao-shun2. WPD-based blind image steganalysis[J]. 2008, (10): 173-182. DOI：

摘要

基于小波包分解

提出了一类新的具有较高检测正确率的图像信息隐写盲检测方法。首先对图像进行小波包分解得到多个子带

从子带系数以及图像像素中提取直方图特征函数多阶绝对矩作为特征

然后对提取的特征进行预处理并设计BP神经网络分类器进行分类。针对LSB、SS、Jsteg、F5及MB等典型隐写的实验表明:此方法相比现有的典型盲检测方法

正确检测率提高约7.5%

7.2%

且具有更好的通用性。此外

还讨论了整数和非整数小波包分解对检测结果的影响。

Abstract

Based on wavelet package decomposition（WPD）

a new blind image steganalysis method was presented

which can detect the stego images with comparatively high accuracy.Firstly

by three scales of WPD

image was decomposed into some coefficient subbands

and the multi-order absolute characteristic function moments of histogram were extracted as features from these subbands and image itself.And then

these features were processed and a back-propagation（BP） neural network was designed to classify original and stego images.A series of experiments were made to validate the performance of proposed method for five kinds of typical steganography methods

including LSB

Jsteg

F5 and MB.Results show the method can detect stego and original images reliably

and the average detection accuracy of this method exceeds those of its closest competitors by at least 7.5% and up to 17.2%.Moreover

the influence of integral and non-integral WPD for the detection accuracy was discussed.

关键词

Keywords

references

Views

901

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Metric and classification model for privacy data based on Shannon information entropy and BP neural network

Proof of work algorithm based on credit model

Approach of detecting low-rate DoS attack based on combined features

False traffic information detection based on weak classifiers integration in vehicular ad hoc networks

Blind audio watermarking mechanism based on variational Bayesian learning

Related Author

Xiaoping WU

Yu FU

Yihan YU

Xinhuan YANG

Qiuxian LI

Youliang TIAN

Zuan WANG

Zhi-jun WU

Related Institution

Naval University of Engineering

College of Computer Science ＆Technology,Guizhou University

Guizhou Provincial Key Labortory of Public Big Data (Guizhou University)

Institute of Cryptography ＆Data Security, Guizhou University

College of Electronics Information and Automation,Civil Aviation University of China

AI问答

⁰