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

作　　者：王金伟[1] 胡冰涛 张家伟 马宾[2] 罗向阳 WANG Jin-wei;HU Bing-tao;ZHANG Jia-wei;MA Bin;LUO Xiang-yang(School of Computer Science,Nanjing University of Information Science and Technology,Nanjing,Jiangsu 210044,China;Shandong Provincial Key Laboratory of Computer Networks,Qilu University of Technology,Jinan,Shandong 250353,China;State Key Laboratory of Mathematical Engineering and Advanced Computing,Zhengzhou,Henan 450001,China)

机构地区：[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

出　　处：《电子学报》2023年第4期850-859,共10页Acta Electronica Sinica

基　　金：国家自然科学基金(No.62072250,No.62172435,No.U1804263,No.U20B2065,No.61872203,No.71802110,No.61802212);中原科技创新领军人才项目(No.214200510019);江苏省自然科学基金(No.BK20200750);河南省网络空间态势感知重点实验室开放基金(No.HNTS2022002);江苏省研究生研究与实践创新项目(No.KYCX200974);广东省信息安全技术重点实验室开放项目(No.2020B1212060078);山东省计算机网络重点实验室开放课题基金(No.SDKLCN-2022-05);人文社会科学教育部项目(No.19YJA630061);江苏高校优势学科建设工程项目。

摘　　要：现有的基于深度学习的同步JPEG(JointPhotographic ExpertsGroup)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%.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 clas-sification basis.Pre-processing layers that reduce the difficulty of feature extraction are present before the detection frame-work,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 decompres-sion 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：数字图像取证 卷积神经网络 JPEG重压缩 解压缩模块 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]