彩色图像JPEG重压缩取证综述

doi:10.11772/j.issn.1001-9081.2024111614

《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (11): 3609-3620.DOI: 10.11772/j.issn.1001-9081.2024111614

• 网络空间安全 • 上一篇

彩色图像JPEG重压缩取证综述

王昊¹, 王金伟¹^,², 程鑫³(), 张家伟⁴, 吴昊⁵, 罗向阳⁵, 马宾⁶

^1.南京理工大学自动化学院，南京 210094
^2.南开大学网络空间安全学院，天津 300350
^3.南京信息工程大学计算机学院、网络空间安全学院，南京 210044
^4.重庆邮电大学网络空间安全与信息法学院，重庆 400065
^5.数学工程与先进计算国家重点实验室（信息工程大学），郑州 450001
^6.齐鲁工业大学网络空间安全学院，济南 250353

收稿日期:2024-11-13 修回日期:2024-12-06 接受日期:2024-12-20 发布日期:2025-01-03 出版日期:2025-11-10
通讯作者: 程鑫
作者简介:王昊（1995—），男，江苏连云港人，讲师，博士，主要研究方向：信息安全、JPEG压缩取证
王金伟（1978—），男，山东烟台人，教授，博士，主要研究方向：人工智能安全、多媒体取证
张家伟（1996—），男，江苏南京人，讲师，博士，主要研究方向：对抗样本取证、JPEG压缩取证
吴昊（1999—），男，江苏南京人，博士研究生，主要研究方向：对抗样本取证、JPEG压缩取证
罗向阳（1978—），男，湖北荆门人，教授，博士，主要研究方向：图像隐写、隐写分析
马宾（1973—），男，山东济南人，教授，博士，主要研究方向：可逆信息隐藏、多媒体取证、隐写与隐写分析。
基金资助:
国家自然科学基金资助项目(62472229);江苏省研究生研究与实际创新项目(KYCX24_1513);省部共建藏语智能信息处理及应用国家重点实验室（藏文信息处理教育部重点实验室）开放课题(2024-Z-003)

Review of JPEG recompression forensics for color images

Hao WANG¹, Jinwei WANG¹^,², Xin CHENG³(), Jiawei ZHANG⁴, Hao WU⁵, Xiangyang LUO⁵, Bin MA⁶

^1.School of Automation，Nanjing University of Science and Technology，Nanjing Jiangsu 210094，China
^2.College of Cryptology and Cyber Science，Nankai University，Tianjin 300350，China
^3.School of Computer Science，Cyber Science and Engineering，Nanjing University of Information Science and Technology，Nanjing Jiangsu 210044，China
^4.School of Cyber Security and Information Law，Chongqing University of Posts and Telecommunications，Chongqing 400065，China
^5.State Key Laboratory of Mathematical Engineering and Advanced Computing （Information Engineering University），Zhengzhou Henan 450001，China
^6.School of Cyber Security，Qilu University of Technology，Jinan Shandong 250353，China

Received:2024-11-13 Revised:2024-12-06 Accepted:2024-12-20 Online:2025-01-03 Published:2025-11-10
Contact: Xin CHENG
About author:WANG Hao， born in 1995， Ph. D.， lecturer. His research interests include information security， JPEG compression forensics.
WANG Jinwei， born in 1978， Ph. D.， professor. His research interests include artificial intelligence security， multimedia forensics.
ZHANG Jiawei， born in 1996， Ph. D.， lecturer. His research interests include adversarial sample forensics， JPEG compression forensics.
WU Hao， born in1999， Ph. D. candidate. His research interests include adversarial sample forensics， JPEG compression forensics.
LUO Xiangyang， born in 1978， Ph. D.， professor. His research interests include image steganography， steganalysis.
MA Bin， born in 1973， Ph. D.， professor. His research interests include reversible information hiding， multimedia forensics， steganography and steganalysis.
Supported by:
National Natural Science Foundation of China(62472229);Postgraduate Research and Practice Innovation Program of Jiangsu Province(KYCX24_1513);Open Foundation of the State Key Laboratory of Tibetan Intelligent Information Processing and Application（Key Laboratory of Tibetan Information Processing, Ministry of Education）(2024-Z-003)

摘要/Abstract

摘要：

JPEG（Joint Photographic Experts Group）压缩是当前应用最为广泛的图像压缩标准之一，它涉及诸如图像操作链取证、图像源取证、隐写与隐写分析和JPEG反取证等多种取证场景和安全模型。研究者针对JPEG图像特性开展了诸多有关JPEG重压缩取证的研究，发现JPEG重压缩取证不仅为图像取证提供先验知识，也可以直接应用到取证场景中。因此，对彩色图像JPEG重压缩取证进行综述。首先，介绍了重压缩取证的研究背景，并将重压缩取证分成了非对齐、对齐异步和对齐同步3种重压缩问题；其次，详细介绍了JPEG压缩的流程、收敛误差、误差图像、算法评价指标等用于重压缩取证的基础知识；再次，对每类问题的现有方法进行了详细的介绍和梳理。此外，由于图像隐写、对抗样本等都涉及关于JPEG重压缩的鲁棒性研究，因此，列举了JPEG重压缩特征特性在上述领域中的应用，并选取了常见的算法进行对比，总结归纳它们的优缺点。最后，展望了JPEG重压缩取证中有待进一步解决的问题和发展趋势。

关键词: 数字取证, JPEG重压缩取证, JPEG压缩流程, 误差图像, 收敛误差

Abstract:

The JPEG （Joint Photographic Experts Group） compression is one of the most widely used image compression standards and is involved in various forensic scenarios and security models such as image operation chain forensics， image source forensics， steganography， steganalysis， and JPEG anti-forensics. Researchers have conducted extensive studies on JPEG recompression forensics based on the characteristics of JPEG images， discovering that it not only provides prior knowledge for image forensics but also can be directly applied in forensic scenarios. Therefore， JPEG recompression forensics for color images was reviewed. Firstly， the research background of recompression forensics was introduced， and recompression forensics were classified into three types： non-aligned， aligned asynchronous， and aligned synchronous. Secondly， the basic knowledge required for recompression forensics was detailed， including the JPEG compression process， convergence error， error images， and algorithm evaluation metrics. Furthermore， existing methods for each type of problem were thoroughly reviewed and systematized. Additionally， since fields such as image steganography and adversarial examples involved robustness studies related to JPEG recompression， the applications of JPEG recompression features in these domains were highlighted， and common algorithms were compared to summarize their advantages and disadvantages. Finally， open challenges and future research directions in JPEG recompression forensics were discussed.

Key words: digital forensics, JPEG recompression forensics, JPEG compression process, error image, convergence error

中图分类号:

TP391

王昊, 王金伟, 程鑫, 张家伟, 吴昊, 罗向阳, 马宾. 彩色图像JPEG重压缩取证综述[J]. 计算机应用, 2025, 45(11): 3609-3620.

Hao WANG, Jinwei WANG, Xin CHENG, Jiawei ZHANG, Hao WU, Xiangyang LUO, Bin MA. Review of JPEG recompression forensics for color images[J]. Journal of Computer Applications, 2025, 45(11): 3609-3620.

图/表 10

图1 JPEG压缩参数取证的研究领域

Fig. 1 Research areas of JPEG compression forensics

图2 JPEG压缩和解压缩过程

Fig. 2 Process of JPEG compression and decompression

图3 非对齐JPEG重压缩网格示意图

Fig. 3 Diagram of non-aligned JPEG recompression grid

图4 En获取过程

Fig. 4 Acquisition process of En

图5 Jn的收敛趋势

Fig. 5 Convergence trend of Jn

图6 EBn在相同QF连续压缩下的变化

Fig. 6 Variation of EBn under continuous compression at the same quality factor

图7 En的收敛趋势

Fig. 7 Convergence trend of En

表1 UCID和NRCS数据集上的性能对比

Tab. 1 Performance comparison on UCID and NRCS datasets

$Q F 1$	算法	UCID数据集上的准确率/%					NRCS数据集上的准确率/%
$Q F 1$	算法	$Q F 2 = 50$	$Q F 2 = 60$	$Q F 2 = 70$	$Q F 2 = 80$	$Q F 2 = 90$	$Q F 2 = 50$	$Q F 2 = 60$	$Q F 2 = 70$	$Q F 2 = 80$	$Q F 2 = 90$
50	文献［43］算法	84.51	99.96	100.00	100.00	100.00	85.14	99.91	99.99	99.98	99.99
	文献［40］算法	87.17	89.01	96.86	99.54	99.70	86.94	87.79	96.58	99.69	99.81
	文献［1］算法	81.97	80.23	85.31	90.95	89.70	81.60	81.10	85.61	93.13	85.77
	文献［26］算法	51.61	100.00	99.95	99.99	100.00	50.82	99.99	99.99	100.00	100.00
	文献［14］算法	52.86	99.33	98.96	99.71	100.00	50.76	98.99	99.11	99.37	100.00
	文献［32］算法	50.33	92.57	94.95	98.33	99.84	51.45	96.79	95.16	97.67	99.26
60	文献［43］算法	99.77	84.42	100.00	99.99	99.99	99.59	84.7	99.99	99.98	99.98
	文献［40］算法	82.67	86.59	88.82	99.56	99.65	81.62	87.06	87.73	99.79	99.92
	文献［1］算法	68.31	82.18	81.50	81.40	86.07	62.10	81.40	82.07	89.72	82.28
	文献［26］算法	99.99	51.61	100.00	99.97	100.00	99.99	50.87	100.00	99.99	100.00
	文献［14］算法	98.53	50.06	98.71	99.97	99.99	98.48	50.79	97.63	99.48	100.00
	文献［32］算法	96.02	52.01	94.36	96.46	99.57	93.33	52.80	95.93	98.84	99.26
70	文献［43］算法	99.92	99.79	86.40	99.99	100.00	99.83	99.90	85.23	100.00	100.00
	文献［40］算法	84.25	82.73	88.37	99.31	98.92	85.17	82.87	89.28	99.46	99.13
	文献［1］算法	61.23	64.29	82.34	94.46	73.21	61.62	61.33	83.40	94.10	70.98
	文献［26］算法	99.99	99.99	51.22	99.99	100.00	100.00	100.00	50.89	99.97	100.00
	文献［14］算法	98.91	99.21	53.44	99.89	100.00	98.79	99.41	50.74	99.12	100.00
	文献［32］算法	95.12	90.83	51.04	98.9	99.91	90.88	89.53	50.26	97.25	99.54
80	文献［43］算法	99.57	99.91	99.99	98.43	99.99	99.60	99.93	99.97	98.56	99.99
	文献［40］算法	75.42	82.93	82.64	99.56	99.33	73.20	77.95	81.09	99.28	99.86
	文献［1］算法	56.37	63.27	58.15	96.11	76.04	54.05	64.69	58.83	95.33	81.30
	文献［26］算法	99.99	99.99	100.00	59.31	99.98	100.00	100.00	99.96	58.81	100.00
	文献［14］算法	98.65	99.01	99.86	57.83	99.84	98.37	98.69	99.48	58.85	99.73
	文献［32］算法	97.33	96.89	92.97	54.01	99.58	96.86	94.54	89.31	52.91	99.78
90	文献［43］算法	96.32	99.39	98.88	99.81	98.53	96.62	99.53	98.51	99.83	98.98
	文献［40］算法	62.14	66.09	68.85	93.51	99.01	64.64	65.96	69.27	92.58	99.27
	文献［1］算法	52.43	54.18	54.04	65.99	99.56	50.96	54.09	51.39	62.92	99.31
	文献［26］算法	97.69	99.81	98.98	99.92	76.03	97.57	99.98	99.75	100.00	76.45
	文献［14］算法	93.21	97.88	97.44	98.86	69.54	92.54	95.98	96.75	98.46	59.90
	文献［32］算法	97.78	97.63	94.23	97.49	53.22	94.34	95.28	94.65	91.51	58.66

表1 UCID和NRCS数据集上的性能对比

Tab. 1 Performance comparison on UCID and NRCS datasets

$Q F 1$	算法	UCID数据集上的准确率/%					NRCS数据集上的准确率/%
$Q F 1$	算法	$Q F 2 = 50$	$Q F 2 = 60$	$Q F 2 = 70$	$Q F 2 = 80$	$Q F 2 = 90$	$Q F 2 = 50$	$Q F 2 = 60$	$Q F 2 = 70$	$Q F 2 = 80$	$Q F 2 = 90$
50	文献［43］算法	84.51	99.96	100.00	100.00	100.00	85.14	99.91	99.99	99.98	99.99
	文献［40］算法	87.17	89.01	96.86	99.54	99.70	86.94	87.79	96.58	99.69	99.81
	文献［1］算法	81.97	80.23	85.31	90.95	89.70	81.60	81.10	85.61	93.13	85.77
	文献［26］算法	51.61	100.00	99.95	99.99	100.00	50.82	99.99	99.99	100.00	100.00
	文献［14］算法	52.86	99.33	98.96	99.71	100.00	50.76	98.99	99.11	99.37	100.00
	文献［32］算法	50.33	92.57	94.95	98.33	99.84	51.45	96.79	95.16	97.67	99.26
60	文献［43］算法	99.77	84.42	100.00	99.99	99.99	99.59	84.7	99.99	99.98	99.98
	文献［40］算法	82.67	86.59	88.82	99.56	99.65	81.62	87.06	87.73	99.79	99.92
	文献［1］算法	68.31	82.18	81.50	81.40	86.07	62.10	81.40	82.07	89.72	82.28
	文献［26］算法	99.99	51.61	100.00	99.97	100.00	99.99	50.87	100.00	99.99	100.00
	文献［14］算法	98.53	50.06	98.71	99.97	99.99	98.48	50.79	97.63	99.48	100.00
	文献［32］算法	96.02	52.01	94.36	96.46	99.57	93.33	52.80	95.93	98.84	99.26
70	文献［43］算法	99.92	99.79	86.40	99.99	100.00	99.83	99.90	85.23	100.00	100.00
	文献［40］算法	84.25	82.73	88.37	99.31	98.92	85.17	82.87	89.28	99.46	99.13
	文献［1］算法	61.23	64.29	82.34	94.46	73.21	61.62	61.33	83.40	94.10	70.98
	文献［26］算法	99.99	99.99	51.22	99.99	100.00	100.00	100.00	50.89	99.97	100.00
	文献［14］算法	98.91	99.21	53.44	99.89	100.00	98.79	99.41	50.74	99.12	100.00
	文献［32］算法	95.12	90.83	51.04	98.9	99.91	90.88	89.53	50.26	97.25	99.54
80	文献［43］算法	99.57	99.91	99.99	98.43	99.99	99.60	99.93	99.97	98.56	99.99
	文献［40］算法	75.42	82.93	82.64	99.56	99.33	73.20	77.95	81.09	99.28	99.86
	文献［1］算法	56.37	63.27	58.15	96.11	76.04	54.05	64.69	58.83	95.33	81.30
	文献［26］算法	99.99	99.99	100.00	59.31	99.98	100.00	100.00	99.96	58.81	100.00
	文献［14］算法	98.65	99.01	99.86	57.83	99.84	98.37	98.69	99.48	58.85	99.73
	文献［32］算法	97.33	96.89	92.97	54.01	99.58	96.86	94.54	89.31	52.91	99.78
90	文献［43］算法	96.32	99.39	98.88	99.81	98.53	96.62	99.53	98.51	99.83	98.98
	文献［40］算法	62.14	66.09	68.85	93.51	99.01	64.64	65.96	69.27	92.58	99.27
	文献［1］算法	52.43	54.18	54.04	65.99	99.56	50.96	54.09	51.39	62.92	99.31
	文献［26］算法	97.69	99.81	98.98	99.92	76.03	97.57	99.98	99.75	100.00	76.45
	文献［14］算法	93.21	97.88	97.44	98.86	69.54	92.54	95.98	96.75	98.46	59.90
	文献［32］算法	97.78	97.63	94.23	97.49	53.22	94.34	95.28	94.65	91.51	58.66

表2 UCID和NRCS上的灰盒实验结果

Tab. 2 Grey box experimental results on UCID and NRCS datasets

$Q F 2$	UCID数据集上的准确率/%				NRCS数据集上的准确率/%
$Q F 2$	文献［43］算法	文献［40］算法	文献［26］算法	文献［1］算法	文献［43］算法	文献［40］算法	文献［26］算法	文献［1］算法
50	84.55	70.94	82.91	57.86	85.17	71.57	84.14	54.58
60	90.37	74.58	84.72	62.23	90.54	74.46	84.25	59.03
70	88.77	77.03	84.45	64.53	89.72	78.00	84.48	62.70
80	97.05	95.52	86.03	80.01	96.65	95.47	87.23	82.57
90	98.09	98.11	91.03	78.32	98.60	99.02	93.35	76.95

表2 UCID和NRCS上的灰盒实验结果

Tab. 2 Grey box experimental results on UCID and NRCS datasets

$Q F 2$	UCID数据集上的准确率/%				NRCS数据集上的准确率/%
$Q F 2$	文献［43］算法	文献［40］算法	文献［26］算法	文献［1］算法	文献［43］算法	文献［40］算法	文献［26］算法	文献［1］算法
50	84.55	70.94	82.91	57.86	85.17	71.57	84.14	54.58
60	90.37	74.58	84.72	62.23	90.54	74.46	84.25	59.03
70	88.77	77.03	84.45	64.53	89.72	78.00	84.48	62.70
80	97.05	95.52	86.03	80.01	96.65	95.47	87.23	82.57
90	98.09	98.11	91.03	78.32	98.60	99.02	93.35	76.95

表3 三重压缩取证性能

Tab. 3 Triple compression forensic performance

$Q F$	单压缩和三重压缩的准确率/%			双压缩和三重压缩的准确率/%
$Q F$	文献［43］算法	文献［40］算法	文献［26］算法	文献［43］算法	文献［40］算法	文献［26］算法
50	88.79	82.95	80.82	67.36	63.85	53.24
60	92.56	84.82	86.88	72.08	66.86	54.38
70	93.48	86.33	88.51	69.89	65.31	52.83
80	99.00	97.44	93.28	74.21	70.85	58.91
90	99.34	98.93	97.48	71.69	70.23	65.89

表3 三重压缩取证性能

Tab. 3 Triple compression forensic performance

$Q F$	单压缩和三重压缩的准确率/%			双压缩和三重压缩的准确率/%
$Q F$	文献［43］算法	文献［40］算法	文献［26］算法	文献［43］算法	文献［40］算法	文献［26］算法
50	88.79	82.95	80.82	67.36	63.85	53.24
60	92.56	84.82	86.88	72.08	66.86	54.38
70	93.48	86.33	88.51	69.89	65.31	52.83
80	99.00	97.44	93.28	74.21	70.85	58.91
90	99.34	98.93	97.48	71.69	70.23	65.89

参考文献 81

[1]	NIU Y， LI X， ZHAO Y， et al. Detection of double JPEG compression with the same quantization matrix via convergence analysis［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2022， 32（5）： 3279-3290.
[2]	LUO W， QU Z， HUANG J， et al. A novel method for detecting cropped and recompressed image block［C］// Proceedings of the 2007 IEEE International Conference on Acoustics， Speech and Signal Processing — Volume 2. Piscataway： IEEE， 2007： 217-220.
[3]	CHEN Y L， HSU C T. Image tampering detection by blocking periodicity analysis in JPEG compressed images［C］// Proceedings of the IEEE 10th Workshop on Multimedia Signal Processing. Piscataway： IEEE， 2008： 803-808.
[4]	CHEN Y L， HSU C T. Detecting recompression of JPEG images via periodicity analysis of compression artifacts for tampering detection［J］. IEEE Transactions on Information Forensics and Security， 2011， 6（2）： 396-406.
[5]	QU Z， LUO W， HUANG J. A convolutive mixing model for shifted double JPEG compression with application to passive image authentication［C］// Proceedings of the 2008 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2008： 1661-1664.
[6]	BIANCHI T， PIVA A. Analysis of non-aligned double JPEG artifacts for the localization of image forgeries［C］// Proceedings of the 2011 IEEE International Workshop on Information Forensics and Security. Piscataway： IEEE， 2011： 1-6.
[7]	BIANCHI T， PIVA A. Detection of nonaligned double JPEG compression based on integer periodicity maps［J］. IEEE Transactions on Information Forensics and Security， 2012， 7（2）： 842-848.
[8]	TRALIC D， PETROVIC J， GRGIC S. JPEG image tampering detection using blocking artifacts［C］// Proceedings of the 19th International Conference on Systems， Signals and Image Processing. Piscataway： IEEE， 2012： 5-8.
[9]	YANG J， ZHU G， WANG J， et al. Detecting non-aligned double JPEG compression based on refined intensity difference and calibration［C］// Proceedings of the 2013 International Workshop on Digital Watermarking， LNCS 8389. Berlin： Springer， 2014： 169-179.
[10]	WU L， KONG X， WANG B， et al. Image tampering localization via estimating the non-aligned double JPEG compression［C］// Proceedings of the SPIE 8665， Media Watermarking， Security， and Forensics 2013. Bellingham， WA： SPIE， 2013： No.86650R.
[11]	WANG J， HUANG W， LUO X， 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.
[12]	WANG J， HUANG W， LUO X， et al. Detecting non-aligned double JPEG compression based on amplitude-angle feature［J］. ACM Transactions on Multimedia Computing， Communications， and Applications， 2021， 17（4）： No.138.
[13]	WANG Q， ZHANG R. Double JPEG compression forensics based on a convolutional neural network［J］. EURASIP Journal on Information Security， 2016， 2016： No.23.
[14]	BARNI M， BONDI L， BONETTINI N， et al. Aligned and non-aligned double JPEG detection using convolutional neural networks［J］. Journal of Visual Communication and Image Representation， 2017， 49： 153-163.
[15]	LI B， LUO H， ZHANG H， et al. A multi-branch convolutional neural network for detecting double JPEG compression［EB/OL］. ［2024-09-19］..
[16]	VERMA V， AGARWAL N， KHANNA N. DCT-domain deep convolutional neural networks for multiple JPEG compression classification［J］. Signal Processing： Image Communication， 2018， 67： 22-33.
[17]	ALIPOUR N， BEHRAD A. Semantic segmentation of JPEG blocks using a deep CNN for non-aligned JPEG forgery detection and localization［J］. Multimedia Tools and Applications， 2020， 79（11）： 8249-8265.
[18]	LUKÁŠ J， FRIDRICH J. Estimation of primary quantization matrix in double compressed JPEG images［EB/OL］. ［2024-09-19］..
[19]	PEVNY T， RIDRICH J. Detection of double-compression in JPEG images for applications in steganography［J］. IEEE Transactions on Information Forensics and Security， 2008， 3（2）： 247-258.
[20]	POPESCU A C， FARID H. Statistical tools for digital forensics［C］// Proceedings of the 2004 International Workshop on Information Hiding， LNCS 3200. Berlin： Springer， 2005： 128-147.
[21]	FU D， SHI Y Q， SU W. A generalized Benford’s law for JPEG coefficients and its applications in image forensics［C］// Proceedings of the SPIE 6505， Security， Steganography， and Watermarking of Multimedia Contents Ⅸ. Bellingham， WA： SPIE， 2007： No.65051L.
[22]	LI B， SHI Y Q， HUANG J. Detecting doubly compressed JPEG images by using mode based first digit features［C］// Proceedings of the IEEE 10th Workshop on Multimedia Signal Processing. Piscataway： IEEE， 2008： 730-735.
[23]	DONG L， KONG X， WANG B， et al. Double compression detection based on Markov model of the first digits of DCT coefficients［C］// Proceedings of the 6th International Conference on Image and Graphic. Piscataway： IEEE， 2011： 234-237.
[24]	LIU Q， SUNG A H， QIAO M. A method to detect JPEG-based double compression［C］// Proceedings of the 2011 International Symposium on Neural Networks， LNCS 6676. Berlin： Springer， 2011： 466-476.
[25]	SHANG S， ZHAO Y， NI R. Double JPEG detection using high order statistic features［C］// Proceedings of the 2016 IEEE International Conference on Digital Signal Processing. Piscataway： IEEE， 2016： 550-554.
[26]	LI J， LU W， WENG J， et al. Double JPEG compression detection based on block statistics［J］. Multimedia Tools and Applications， 2018， 77（24）： 31895-31910.
[27]	TAIMORI A， RAZZAZI F， BEHRAD A， et al. A part-level learning strategy for JPEG image recompression detection［J］. Multimedia Tools and Applications， 2021， 80（8）： 12235-12247.
[28]	PARK J， CHO D， AHN W， et al. Double JPEG detection in mixed JPEG quality factors using deep convolutional neural network［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11209. Cham： Springer， 2018： 656-672.
[29]	ZENG X， FENG G， ZHANG X. Detection of double JPEG compression using modified DenseNet model［J］. Multimedia Tools and Applications， 2019， 78（7）： 8183-8196.
[30]	DENG C， LI Z， GAO X， et al. Deep multi-scale discriminative networks for double JPEG compression forensics［J］. ACM Transactions on Intelligent Systems and Technology， 2019， 10（2）： No.20.
[31]	LI B， ZHANG H， LUO H， et al. Detecting double JPEG compression and its related anti-forensic operations with CNN［J］. Multimedia Tools and Applications， 2019， 78（7）： 8577-8601.
[32]	HUSSAIN I， TAN S， LI B， et al. A novel deep learning framework for double JPEG compression detection of small size blocks［J］. Journal of Visual Communication and Image Representation， 2021， 80： No.103269.
[33]	VERMA V， SINGH D， KHANNA N. Block-level double JPEG compression detection for image forgery localization［J］. Multimedia Tools and Applications， 2024， 83（4）： 9949-9971.
[34]	BI X， YAN W， LIU B， et al. Self-supervised image local forgery detection by JPEG compression trace［C］// Proceedings of the 2023 AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2023： 232-240.
[35]	HUANG F， HUANG J， 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.
[36]	LAI S， BÖHME R. Block convergence in repeated transform coding： JPEG-100 forensics， carbon dating， and tamper detection［C］// Proceedings of the 2013 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2013： 3028-3032.
[37]	YANG J， XIE J， ZHU G， 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.
[38]	NIU Y， LI X， 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.
[39]	WANG J， 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.
[40]	WANG H， WANG J， LUO X， 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.
[41]	CHAI X， TAN Y， JIANG W， et al. Detecting aligned double JPEG compression with the same quantization matrix based on Hamming distance and image stability［C］// Proceedings of the 2023 IEEE International Conference on Signal Processing， Communications and Computing. Piscataway： IEEE， 2023： 1-5.
[42]	CHAI X， TAN Y， GAN Z， et al. Forgery detection using polynomial fitting in recompressed JPEG images［J］. Signal， Image and Video Processing， 2024， 18（3）： 2439-2451.
[43]	WANG H， WANG J， ZHANG J， et al. General forensics for aligned double JPEG compression based on the quantization interference［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2024， 34（6）： 5191-5206.
[44]	HUANG X， WANG S， LIU G. Detecting double JPEG compression with same quantization matrix based on dense CNN feature［C］// Proceedings of the 25th IEEE International Conference on Image Processing. Piscataway： IEEE， 2018： 3813-3817.
[45]	PENG P， SUN T， JIANG X， et al. Detection of double JPEG compression with the same quantization matrix based on convolutional neural networks［C］// Proceedings of the 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Piscataway： IEEE， 2018： 717-721.
[46]	WANG H， WANG J， ZHAI J， et al. Detection of triple JPEG compressed color images［J］. IEEE Access， 2019， 7： 113094-113102.
[47]	DESHPANDE A U， HARISH A N， SINGH S， et al. Neural network based block-level detection of same quality factor double JPEG compression［C］// Proceedings of the 7th International Conference on Signal Processing and Integrated Networks. Piscataway： IEEE， 2020： 828-833.
[48]	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（4）： 850-859.
	WANG J W， HU B T， ZHANG J W， et al. JPEG synchronous double compression detection based on decompression module［J］. Acta Electronica Sinica， 2023， 51（4）： 850-859.
[49]	ZHAO X， MENG X， REN R， et al. Detecting double JPEG compressed color images via an improved approach［J］. Computers， Materials and Continua， 2023， 75（1）： 1765-1781.
[50]	BILLA N R， DAS B P， BISWAL M， et al. CNN based image resizing forensics for double compressed JPEG images［J］. Journal of Information Security and Applications， 2024， 81： No.103693.
[51]	SZEGEDY C， ZAREMBA W， SUTSKEVER I， et al. Intriguing properties of neural networks［EB/OL］. ［2024-04-10］..
[52]	CARLINI N， WAGNER D. Towards evaluating the robustness of neural networks［C］// Proceedings of the 2017 IEEE Symposium on Security and Privacy. Piscataway： IEEE， 2017： 39-57.
[53]	GOODFELLOW I J， SHLENS J， SZEGEDY C. Explaining and harnessing adversarial examples［EB/OL］. ［2024-06-07］..
[54]	MADRY A， MAKELOV A， SCHMIDT L， et al. Towards deep learning models resistant to adversarial attacks［EB/OL］. ［2024-09-19］..
[55]	KURAKIN A， GOODFELLOW I J， BENGIO S. Adversarial examples in the physical world［M］// YAMPOLSKIY R V. Artificial intelligence safety and security. New York： Chapman， 2018： 99-112.
[56]	XIAO C， LI B， ZHU J Y， et al. Generating adversarial examples with adversarial networks［C］// Proceedings of the 27th International Joint Conference on Artificial Intelligence. California： IJCAI.org， 2018： 3905-3911.
[57]	XU W， EVANS D， QI Y. Feature squeezing： detecting adversarial examples in deep neural networks［C］// Proceedings of the 2018 Annual Network and Distributed Systems Security Symposium. Reston， VA： Internet Society， 2018： 1-15.
[58]	MO H， SONG T， CHEN B， et al. Enhancing JPEG steganography using iterative adversarial examples［C］// Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security. Piscataway： IEEE， 2019： 1-6.
[59]	WANG J， ZHAO J， YIN Q， et al. SmsNet： a new deep convolutional neural network model for adversarial example detection［J］. IEEE Transactions on Multimedia， 2022， 24： 230-244.
[60]	TSUNOMORI K， YAMASAKI Y， KURIBAYASHI M， et al. Detection and correction of adversarial examples based on IPEG-compression-derived distortion［C］// Proceedings of the 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. Piscataway： IEEE， 2022： 1831-1836.
[61]	赵俊杰，王金伟，吴俊凤.基于多质量因子压缩误差的对抗样本攻击方法识别［J］.中国图象图形学报，2023，28（3）：850-863.
	ZHAO J J， WANG J W， WU J F. Adversarial attack method identification model based on multi-factor compression error［J］. Journal of Image and Graphics， 2023， 28（3）： 850-863.
[62]	ZHAO J， WU J， ADEKE J M， et al. Detecting high-resolution adversarial images with few-shot deep learning［J］. Remote Sensing， 2023， 15（9）： No.2379.
[63]	KODOVSKÝ J， FRIDRICH J. Steganalysis of JPEG images using rich models［C］// Proceedings of the SPIE 8303， Media Watermarking， Security， and Forensics 2012. Bellingham， WA： SPIE， 2012： No.83030A.
[64]	PEVNY T， FRIDRICH J. Merging Markov and DCT features for multi-class JPEG steganalysis［C］// Proceedings of the SPIE 6505， Security， Steganography， and Watermarking of Multimedia Contents Ⅸ. Bellingham， WA： SPIE， 2007： No.650503.
[65]	KODOVSKÝ J， FRIDRICH J. Calibration revisited［C］// Proceedings of the 11th ACM Workshop on Multimedia and Security. New York： ACM， 2009： 63-74.
[66]	ZHAO Z， GUAN Q， ZHANG H， et al. Improving the robustness of adaptive steganographic algorithms based on transport channel matching［J］. IEEE Transactions on Information Forensics and Security， 2019， 14（7）： 1843-1856.
[67]	SHI Y Q， CHEN C， CHEN W， et al. Effect of recompression on attacking JPEG steganographic schemes an experimental study［C］// Proceedings of the 2007 IEEE International Symposium on Circuits and Systems. Piscataway： IEEE， 2007： 1265-1268.
[68]	HOLUB V， FRIDRICH J. Low-complexity features for JPEG steganalysis using undecimated DCT［J］. IEEE Transactions on Information Forensics and Security， 2015， 10（2）： 219-228.
[69]	SONG X， LIU F， YANG C， et al. Steganalysis of adaptive JPEG steganography using 2D Gabor filters［C］// Proceedings of the 3rd ACM Workshop on Information Hiding and Multimedia Security. New York： ACM， 2015： 15-23.
[70]	ZENG J， TAN S， LI B， et al. Large-scale JPEG image steganalysis using hybrid deep-learning framework［J］. IEEE Transactions on Information Forensics and Security， 2018， 13（5）： 1200-1214.
[71]	XU G. Deep convolutional neural network to detect J-UNIWARD［C］// Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security. New York： ACM， 2017： 67-73.
[72]	BOROUMAND M， CHEN M， FRIDRICH J. Deep residual network for steganalysis of digital images［J］. IEEE Transactions on Information Forensics and Security， 2019， 14（5）： 1181-1193.
[73]	BUTORA J， FRIDRICH J. Reverse JPEG compatibility attack［J］. IEEE Transactions on Information Forensics and Security， 2020， 15： 1444-1454.
[74]	FENG J， WANG Y， CHEN K， et al. An effective steganalysis for robust steganography with repetitive JPEG compression［C］// Proceedings of the 2022 IEEE International Conference on Acoustics， Speech and Signal Processing. Piscataway： IEEE， 2022： 3084-3088.
[75]	GUAN Q， CHEN K， CHEN H， et al. Detecting steganography in JPEG images recompressed with the same quantization matrix［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2022， 32（9）： 6002-6016.
[76]	TAN M， LE Q V. EfficientNet： rethinking model scaling for convolutional neural network［C］// Proceedings of the 36th International Conference on Machine Learning. New York： JMLR.org， 2019： 6105-6114.
[77]	FU T， CHEN L， GAO Y， et al. DCANet： CNN model with dual-path network and improved coordinate attention for JPEG steganalysis［J］. Multimedia Systems， 2024， 30（4）： No.230.
[78]	LIU X， LI W， LIN K， et al. Spatial-frequency feature fusion network for lightweight and arbitrary-sized JPEG steganalysis［J］. IEEE Signal Processing Letters， 2024， 31： 2585-2589.
[79]	SCHAEFER G， STICH M. UCID： an uncompressed color image database［C］// Proceedings of the SPIE 5307， Storage and Retrieval Methods and Applications for Multimedia 2004. Bellingham， WA： SPIE， 2003： 472-480.
[80]	NRCS photo gallery［DS/OL］. ［2024-07-21］..
[81]	D-T DANG-NGUYEN， PASQUINI C， CONOTTER V， et al. RAISE： a raw images dataset for digital image forensics［C］// Proceedings of the 6th ACM Multimedia Systems Conference. New York： ACM， 2015： 219-224.

彩色图像JPEG重压缩取证综述

Review of JPEG recompression forensics for color images

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 81

相关文章 1

编辑推荐

Metrics