A New Video Steganalysis Algorithm against Motion Vector Steganography

2008 ◽  
Author(s):  
Chengqian Zhang ◽  
Yuting Su ◽  
Chuntian Zhang
Keyword(s):  
Motion Vector ◽  
Video Steganalysis

Digital video steganalysis using motion vector recovery-based features

2012 ◽  
Vol 51 (20) ◽  
pp. 4667 ◽  
Author(s):  
Yu Deng ◽  
Yunjie Wu ◽  
Linna Zhou
Keyword(s):  
Digital Video ◽  
Motion Vector ◽  
Video Steganalysis

Domain Adaptation for Video Steganalysis against Motion Vector Based Steganography

2014 ◽  
Vol 998-999 ◽  
pp. 1138-1145
Author(s):  
Ke Ren Wang ◽  
Wen Xiang Li
Keyword(s):  
Real World ◽  
Domain Adaptation ◽  
Motion Vector ◽  
Component Analysis ◽  
Potential Effect ◽  
Opposite Case ◽  
Real World Applications ◽  
Performance Results ◽  
Video Steganalysis

Video steganalysis takes effect when videos corrupted by the target steganography method are available. Nevertheless, classical classifiers deteriorate in the opposite case. This paper presents a method to cope with the problem of steganography method mismatch for the detection of motion vector (MV) based steganography. Firstly, Adding-or-Subtracting-One (AoSO) feature against MV based steganography and Transfer Component Analysis (TCA) for domain adaptation are revisited. Distributions of AoSO feature against various MV based steganography methods are illustrated, followed by the potential effect of TCA based AoSO feature. Finally, experiments are carried out on various cases of steganography method mismatch. Performance results demonstrate that TCA+AoSO feature significantly outperforms AoSO feature, and is more favorable for real-world applications.

Video Steganalysis Exploiting Motion Vector Calibration-Based Features

2012 ◽  
Vol 482-484 ◽  
pp. 168-172 ◽  
Author(s):  
Yu Deng ◽  
Yun Jie Wu ◽  
Lin Na Zhou
Keyword(s):  
Support Vector Machine ◽  
Feature Vector ◽  
Motion Vector ◽  
Support Vector ◽  
Motion Vectors ◽  
Feature Vectors ◽  
Video Steganalysis

The motion vector (MV)-based steganography embeds the secret messages by modifying the motion vectors. So the traditional video steganalytic schemes cannot detect the presence of the hidden messages by MV-based steganography. In this paper, a novel calibration-based steganalytic scheme against MV-based steganography is presented. The features are derived from the shift differences between the original and calibrated MVs, and then the feature vector is constructed. Using the extracted feature vectors, the support vector machine (SVM) is trained to detect the presence of stego videos. Compared with other features, the proposed features have better performance even with the low embedding strength.

Digital video steganalysis based on motion vector statistical characteristics

Optik ◽  
2013 ◽  
Vol 124 (14) ◽  
pp. 1705-1710 ◽  
Author(s):  
Yu Deng ◽  
Yunjie Wu ◽  
Haibin Duan ◽  
Linna Zhou
Keyword(s):  
Digital Video ◽  
Motion Vector ◽  
Statistical Characteristics ◽  
Video Steganalysis

Video Steganalysis Exploiting Motion Vector Reversion-Based Features

2012 ◽  
Vol 19 (1) ◽  
pp. 35-38 ◽  
Author(s):  
Yun Cao ◽  
Xianfeng Zhao ◽  
Dengguo Feng
Keyword(s):  
Motion Vector ◽  
Video Steganalysis

scholarly journals Segmentation Based Video Steganalysis to Detect Motion Vector Modification

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Peipei Wang ◽  
Yun Cao ◽  
Xianfeng Zhao
Keyword(s):  
Motion Vector ◽  
Experimental Results ◽  
Statistical Characteristics ◽  
Video Content ◽  
Video Steganography ◽  
Fixed Length ◽  
Content Diversity ◽  
The Given ◽  
Video Steganalysis ◽  
Content Adaptive

This paper presents a steganalytic approach against video steganography which modifies motion vector (MV) in content adaptive manner. Current video steganalytic schemes extract features from fixed-length frames of the whole video and do not take advantage of the content diversity. Consequently, the effectiveness of the steganalytic feature is influenced by video content and the problem of cover source mismatch also affects the steganalytic performance. The goal of this paper is to propose a steganalytic method which can suppress the differences of statistical characteristics caused by video content. The given video is segmented to subsequences according to block’s motion in every frame. The steganalytic features extracted from each category of subsequences with close motion intensity are used to build one classifier. The final steganalytic result can be obtained by fusing the results of weighted classifiers. The experimental results have demonstrated that our method can effectively improve the performance of video steganalysis, especially for videos of low bitrate and low embedding ratio.

Sign in / Sign up

Export Citation Format

Share Document