Reducing false positives of steganalysis via classification of image-acquiring sources

Pei-tao YANG; Wei-ming ZHANG; Neng-hai YU

doi:10.11959/j.issn.1000-436x.2016282

您当前的位置：

首页 >

文章列表页 >

Reducing false positives of steganalysis via classification of image-acquiring sources

Academic communication | 更新时间：2024-06-05

- Reducing false positives of steganalysis via classification of image-acquiring sources
- Journal on Communications Vol. 37, Issue 12, Pages: 165-170(2016)
- 作者机构：
  
  中国科学技术大学中科院电磁空间信息重点实验室，安徽合肥 230001
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(61502007);The National Natural Science Foundation of China(U1636201);The China Postdoctoral Science Foundation(2015M582015);The Strategic Priority Research Program of the Chinese Academy of Sciences(XDA06030601)
- DOI：10.11959/j.issn.1000-436x.2016282
  CLC： TN309
- Online First：2016-12，
  
  Published：25 December 2016
- 稿件说明：
移动端阅览
Pei-tao YANG, Wei-ming ZHANG, Neng-hai YU. Reducing false positives of steganalysis via classification of image-acquiring sources[J]. Journal on Communications, 2016, 37(12): 165-170.
DOI：

Pei-tao YANG, Wei-ming ZHANG, Neng-hai YU. Reducing false positives of steganalysis via classification of image-acquiring sources[J]. Journal on Communications, 2016, 37(12): 165-170. DOI： 10.11959/j.issn.1000-436x.2016282.

摘要

在实真场景中，在载体失配（CSM

cover source mismatch）条件下降低虚警率是隐写分析的一个巨大挑战，提出了一种新的模型来处理该问题。该方法由来源分类器首先判断图像的来源，继而利用相关来源图像训练而成的隐写分类器判断待测图像是否为载密。在这个过程中，通过对模型参数的调节减小虚警率。实验结果表明，这种方法可以在较大准确率的前提下最小化虚警率。

Abstract

In the real world

reducing false positive rates in the case of cover source mismatch (CSM) was a big challenge for steganalysis. A novel model was proposed to solve the problem. The proposed method determines the im-age-acquiring source firstly by a source detector and then detecting the steg images in each source with a steganalyzer trained for this source. The false positive rate was reduced by solving a parameter model. The experimental results show that this novel method can reach lower false positive rates for larger true positive rates.

关键词

Keywords

references

GOLJAN M , FRIDRICH J , CHEN M . Sensor noise camera identifica-tion: countering counter-forensics [C ] // SPIE Media Forensics and Se-curity II . 2010 : 75410S .

FRIDRICH J . Steganography in digital media: principles, algorithms, and applications [M ] . Cambridge University Press , 2009 .

PEVNY T , KER A D . Towards dependable steganalysis [C ] // SPIE Media Watermarking, Security, and Forensics . 2015 : 94090I .

KODOVSKY J , SEDIGHI V , FRIDRICH J . Study of cover source mismatch in steganalysis and ways to mitigate its impact [C ] // SPIE Media Watermarking, Security, and Forensics . 2014 : 90280J .

BARNI M , CANCELLI G , ESPOSITO A . Forensics aided steganalysis of heterogeneous images [C ] // IEEE Conference Acoustics Speech and Signal Process . 2010 : 1690 - 1693 .

CANCELLI G , DOERR G , BARNI M . A comparative study of ±1 steganalyzers [C ] // IEEE Multimedia Signal Process. Workshop , 2008 : 791 - 794 .

LUBENKO I , KER A D . Steganalysis with mismatched cover: do simple classifiers help [C ] // ACM Workshop on Multimedia and Secu-rity . 2012 : 11 - 18 .

PASQUET J , BRINGAY S , CHAUMONT M . Steganalysis with cover-source mismatch and a small learning database [C ] // 22nd European Signal Processing Conference (EUSIPCO). IEEE , 2014 : 2425 - 2429 .

LI X , KONG X , WANG B . Generalized transfer component analysis for mismatched JPEG steganalysis [C ] // In IEEE International Confer-ence on Image Processing . 2013 : 4432 - 4436 .

ZENG L , KONG X , LI M . JPEG quantization table mismatched stega-nalysis via robust discriminative feature transformation [C ] // In SPIE/IS＆T Electronic Imaging. International Society for Optics and Photonics , 2015 : 94090U .

KER A D , BAS P , FRIDRICH J . Moving steganography and stegana-lysis from the laboratory into the real world [C ] // The 1st ACM Work-shop on Information Hiding and Multimedia Security , 2013 : 45 - 58 .

FRIDRICH J , GOLJAN M . Determining approximate age of digital images using sensor defects [C ] // SPIE Media Watermarking, Security,and Forensics III , 2011 : 788006 .

GOLJAN M , FRIDRICH J , FILLER T . Managing a large database of camera fingerprints [C ] // SPIE Media Forensics and Security II , 2010 : 754108 .

GOLJAN M , FRIDRICH J , CHEN M . Defending against fingerprint-copy attack in sensor-based camera identification [J ] . In IEEE Transactions on Information Security and Forensics . 2010 , 6 ( 1 ): 227 - 236 .

GOLJAN M , FRIDRICH J . Sensor-fingerprint based identification of images corrected for lens distortion [C ] // SPIE Media Watermarking, Security, and Forensics . 2012 : 83030H .

KODOVSKY J , FRIDRICH J , HOLUB V . Ensemble classifiers for steganalysis of digital media [J ] . In IEEE Transaction on Information Forensics and Security , 2012 , 7 ( 2 ): 432 - 444 .

FRIDRICH J , KODOVSKY J . Rich models for steganalysis of digital images [J ] . In IEEE Transactions on Information Forensics and Secu-rity , 2012 , 7 ( 3 ): 868 - 882 .

COGRANNE R , ZITZMANN C , RETRAINT F . Statistical detection of LSB matching using hypothesis testing theory [C ] // The 14th Inter-national Conference on Information Hiding . 2013 : 46 - 62 .

DENEMARK T , FRIDRICH J . Detection of content adaptive LSB matching: a game theory approach [C ] // SPIE Media Watermarking, Security, and Forensics . 2014 : 902804 .

李凤华，殷丽华，吴巍，等．天地一体化信息网络安全保障技术研究进展及发展趋势 [J ] ．通信学报， 2016 , 37 ( 11 ): 156 - 166 .

LI F H , YIN L H , WU W , et al . Research status and development trends of security assurance for space-ground integration information network [J ] . Journal on Communications , 2016 , 37 ( 11 ): 156 - 166 .

Views

1070

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Steganography based on parameters’ disturbance of spatial image transform

Steganalysis of JPEG images using non-linear residuals

Subtractive pixel adjacency matrix based features for steganalysis of spatial color images

Recognition of PQ stego images based on identifiable statistical feature

Video steganalysis scheme based on weighted undirected graph

Related Author

Yao WEI

Neng-hai YU

Wei-ming ZHANG

Xi SUN

Yaqi LIU

Qingxiao GUAN

Xin JIN

Yanshuo ZHANG

Related Institution

Key Laboratory of Electromagnetic Space Information,Chinese Academy of Sciences

School of Information Science and Technology, University of Science and Technology of China

Computer Engineering College, Jimei University

Beijing Electronic Science and Technology Institute

Institute of Cyber Space Security, Information Engineering University

AI问答

⁰