基于解压缩模块的JPEG同步重压缩检测

王金伟; 胡冰涛; 张家伟; 马宾; 罗向阳

doi:10.12263/DZXB.20220424

您当前的位置：

首页 >

文章列表页 >

基于解压缩模块的JPEG同步重压缩检测

学术论文 | 更新时间：2025-12-08

- 基于解压缩模块的JPEG同步重压缩检测
- JPEG Synchronous Double Compression Detection Based on Decompression Module
- 电子学报 2023年51卷第4期页码：850-859
- 作者机构：
  
  1.南京信息工程大学计算机学院、网络空间安全学院，江苏南京 210044
  2.齐鲁工业大学山东省计算机网络重点实验室，山东济南 250353
  3.数学工程与高级计算国家重点实验室，河南郑州 450001
- 作者简介：
  
  [ "王金伟 1978年生，博士、教授、博导.入选江苏省“333高层次人才培养工程”.主要研究方向为人工智能安全、彩色图像取证、彩色图像可逆水印、鲁棒水印和图像加密等.中国电子学会会员编号：E190027579M." ]
  [ "罗向阳（通讯作者） 1978年生，博士、教授、博导，国防科技卓越青年基金获得者，先后入选河南省科技创新杰出青年、杰出人才、中原科技创新领军人才.主要研究方向为网络与信息安全." ]
- 基金信息：
  
  国家自然科学基金(62072250;62172435;U1804263;U20B2065;61872203;71802110;61802212);中原科技创新领军人才项目(214200510019);江苏省自然科学基金(BK20200750);河南省网络空间态势感知重点实验室开放基金(HNTS2022002);江苏省研究生研究与实践创新项目(KYCX200974);广东省信息安全技术重点实验室开放项目(2020B1212060078);山东省计算机网络重点实验室开放课题基金(SDKLCN-2022-05);人文社会科学教育部项目(19YJA630061);江苏高校优势学科建设工程项目
- DOI：10.12263/DZXB.20220424
  中图分类号： TP751.1;
- 收稿：2022-04-18，
  
  修回：2022-10-10，
  
  纸质出版：2023-04-25
- 稿件说明：
移动端阅览
王金伟,胡冰涛,张家伟等.基于解压缩模块的JPEG同步重压缩检测[J].电子学报,2023,51(04):850-859.

WANG Jin-wei,HU Bing-tao,ZHANG Jia-wei,et al.JPEG Synchronous Double Compression Detection Based on Decompression Module[J].ACTA ELECTRONICA SINICA,2023,51(04):850-859.
王金伟,胡冰涛,张家伟等.基于解压缩模块的JPEG同步重压缩检测[J].电子学报,2023,51(04):850-859. DOI： 10.12263/DZXB.20220424.

WANG Jin-wei,HU Bing-tao,ZHANG Jia-wei,et al.JPEG Synchronous Double Compression Detection Based on Decompression Module[J].ACTA ELECTRONICA SINICA,2023,51(04):850-859. DOI： 10.12263/DZXB.20220424.

摘要

现有的基于深度学习的同步JPEG（Joint Photographic Experts Group）重压缩检测算法大多使用解压缩过程中产生的截断和舍入误差作为分类依据，在检测框架前都存在降低特征提取难度的预处理层，无法实现端到端.同时，现有的量化底表是根据人为经验所设计的，无法取得解压缩过程的最优解，限制了JPEG重压缩检测算法的精度上限.针对这些问题，本文提出了一种基于解压缩模块的JPEG重压缩检测方法，该方法利用卷积模拟JPEG解压缩过程，设计了解压缩模块，将JPEG解压缩过程并入网络中从而实现端到端，省去了繁重的预处理步骤；同时，利用深度学习能够自动优化参数的特性，自动去寻找解压缩过程的最优解，减少了由于人工处理导致的图像信息的二次损失，进一步提升了JPEG重压缩检测算法的性能上限.实验结果表明，本文所提出的JPEG同步重压缩检测算法在超过半数的实验组上都取得了较好的取证表现，在UCID数据集上比现有方法平均精度最多提高1.8%.

Abstract

Most of the existing deep learning-based synchronous JPEG (Joint Photographic Experts Group) double compression detection algorithms use the truncation and rounding errors generated in the decompression process as the classification basis. Pre-processing layers that reduce the difficulty of feature extraction are present before the detection framework

and end-to-end detection cannot be achieved. Meanwhile

the existing quantization base table is designed based on human experience and cannot obtain the optimal solution for the decompression process

which limits the accuracy of the JPEG double compression detection algorithms. To address these issues

a JPEG double compression detection method based on a decompression module is proposed. The proposed method exploits convolution to simulate the JPEG decompression process

and designs the decompression module to incorporate the JPEG decompression process into the network to achieve end-to-end detection

which is free from laborious pre-processing steps. At the same time

the optimal solution for the decompression process is automatically searched based on the self-optimized characteristic of deep learning

which can reduce the secondary loss of image information caused by manual processing and further improve the performance of the JPEG double compression detection algorithm. The experimental results show that the proposed synchronous JPEG double compression detection algorithm achieves better forensic performance in more than half of the experimental groups

with an average accuracy improvement of up to 1.8% over against the existing methods on the UCID dataset.

关键词

Keywords

references

AYABURI E W , TREKU D N . Effect of penitence on social media trust and privacy concerns: The case of Facebook [J ] . International Journal of Information Management , 2020 , 50 : 171 - 181 .

ZHANG Q B , LU W , WENG J . Joint image splicing detection in DCT and Contourlet transform domain [J ] . Journal of Visual Communication and Image Representation , 2016 , 40 : 449 - 458 .

CHEN B J , COATRIEUX G , WU J S , et al . Fast computation of sliding discrete tchebichef moments and its application in duplicated regions detection [J ] . IEEE Transactions on Signal Processing , 2015 , 63 ( 20 ): 5424 - 5436 .

LI J , LI X L , YANG B , et al . Segmentation-based image copy-move forgery detection scheme [J ] . IEEE Transactions on Information Forensics and Security , 2015 , 10 ( 3 ): 507 - 518 .

LUKÁŠ J , FRIDRICH J . Estimation of primary quantization matrix in double compressed JPEG images [J ] . Digital Forensic Research , 2003 : 5 - 8 .

POPESCU A C , FARID H . Statistical tools for digital forensics [C ] // International Workshop on Information Hiding . Toronto : Springer , 2004 : 128 - 147 .

FU D D , SHI Y Q , SU W . A generalized Benford's law for JPEG coefficients and its applications in image forensics [C ] // Proceedings of Security, Steganography, and Watermarking of Multimedia Contents IX . San Jose : SPIE , 2007 : 574 - 584 .

LI B , SHI Y Q , HUANG J W . Detecting doubly compressed JPEG images by using mode based first digit features [C ] // 2008 IEEE 10th Workshop on Multimedia Signal Processing . Cairns : IEEE , 2008 : 730 - 735 .

AMERINI I , BECARELLI R , CALDELLI R , et al . Splicing forgeries localization through the use of first digit features [C ] // 2014 IEEE International Workshop on Information Forensics and Security (WIFS) . Atlanta : IEEE , 2014 : 143 - 148 .

TAIMORI A , RAZZAZI F , BEHRAD A , et al . A novel forensic image analysis tool for discovering double JPEG compression clues [J ] . Multimedia Tools and Applications , 2017 , 76 ( 6 ): 7749 - 7783 .

WANG J W , HUANG W , LUO X Y , et al . Non-aligned double JPEG compression detection based on refined Markov features in QDCT domain [J ] . Journal of Real-Time Image Processing , 2020 , 17 ( 1 ): 7 - 16 .

YAO H , WEI H B , QIN C , et al . An improved first quantization matrix estimation for nonaligned double compressed JPEG images [J ] . Signal Processing , 2020 , 170 : 107430 .

LIU X J , LU W , XUE Y J , et al . Upscaling factor estimation on double JPEG compressed images [J ] . Multimedia Tools and Applications , 2020 , 79 ( 19 ): 12891 - 12914 .

HUANG F J , HUANG J W , SHI Y Q . Detecting double JPEG compression with the same quantization matrix [J ] . IEEE Transactions on Information Forensics and Security , 2010 , 5 ( 4 ): 848 - 856 .

NIU Y K , LI X L , ZHAO Y , et al . An enhanced approach for detecting double JPEG compression with the same quantization matrix [J ] . Signal Processing: Image Communication , 2019 , 76 : 89 - 96 .

LAI S Y , BÖHME R . Block convergence in repeated transform coding: JPEG-100 forensics, carbon dating, and tamper detection [C ] // 2013 IEEE International Conference on Acoustics, Speech and Signal Processing . Vancouver : IEEE , 2013 : 3028 - 3032 .

YANG J Q , XIE J , ZHU G P , et al . An effective method for detecting double JPEG compression with the same quantization matrix [J ] . IEEE Transactions on Information Forensics and Security , 2014 , 9 ( 11 ): 1933 - 1942 .

PENG P , SUN T F , JIANG X H , et al . Detection of double JPEG compression with the same quantization matrix based on convolutional neural networks [C ] // 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) . Honolulu : IEEE , 2018 : 717 - 721 .

WANG Z F , ZHU L , MIN Q S , et al . Double compression detection based on feature fusion [C ] // 2017 International Conference on Machine Learning and Cybernetics (ICMLC) . Honolulu : IEEE , 2017 : 379 - 384 .

HUANG X S , WANG S L , LIU G S . Detecting double jpeg compression with same quantization matrix based on dense cnn feature [C ] // 2018 25th IEEE International Conference on Image Processing (ICIP) . Athens : IEEE , 2018 : 3813 - 3817 .

WANG J W , WANG H , LI J , et al . Detecting double JPEG compressed color images with the same quantization matrix in spherical coordinates [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2020 , 30 ( 8 ): 2736 - 2749 .

DESHPANDE A U , HARISH A N , SINGH S , et al . Neural network based block-level detection of same quality factor double JPEG compression [C ] // 2020 7th International Conference on Signal Processing and Integrated Networks (SPIN) . Noida : IEEE , 2020 : 828 - 833 .

SCHAEFER G , STICH M . UCID: An uncompressed color image database [C ] // Proceedings of Storage and Retrieval Methods and Applications for Multimedia . San Jose : SPIE , 2003 : 472 - 480 .

WANG H , WANG J W , LUO X Y , et al . Detecting aligned double JPEG compressed color image with same quantization matrix based on the stability of image [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2022 , 32 ( 6 ): 4065 - 4080 .

王昊 . 彩色图像同步JPEG重压缩检测研究 [D ] . 南京 : 南京信息工程大学 , 2020 .

WANG H . Research on Detecting Double JPEG Compressed Image with the Same Quantization Matrix [D ] . Nanjing : Nanjing University of Information Science & Technology , 2020 . (in Chinese)

MALVAR H S , HALLAPURO A , KARCZEWICZ M , et al . Low-complexity transform and quantization in H.264/AVC [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2003 , 13 ( 7 ): 598 - 603 .

WALLACE G K . The JPEG still picture compression standard [J ] . Communications of the ACM , 1991 , 34 ( 4 ): 30 - 44 .

NRCS Photo Gallery [EB/OL ] . ( 2017-12-07 )[ 2022-04 ] . http://photogallery.nrcs.usda.gov http://photogallery.nrcs.usda.gov .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于非一般类算子融合方法及硬件架构设计

共享超分的双分支遥感图像时空融合网络

基于轻量级全连接张量映射网络的高光谱图像分类方法

Cross-CNN：基于CNN和Transformer混合模型的动画跨帧线稿着色算法