Advancing Quantization Steps Estimation: A Two-Stream Network Approach for Enhancing Robustness
Authors: 
Xin Cheng, Hao Wang, Jinwei Wang, Xiangyang Luo, Bin MaAuthors Info & Claims
Pages 6540 - 6548
Abstract
In Joint Photographic Experts Group (JPEG) image steganalysis and forensics, the quantization step can reveal the history of image operations. Several methods for estimating the quantization step have been proposed by researchers. However, existing algorithms fail to account for robustness, which limits the application of these algorithms. To solve the above problems, we propose a two-stream network structure based on Swin Transformer. The spatial domain features of JPEG images exhibit strong robustness but low accuracy. Conversely, frequency domain features demonstrate high accuracy but weak robustness. Therefore, we design a two-stream network with the multi-scale feature of Swin Transformer to extract spatial domain features with high robustness and frequency domain features with high accuracy, respectively. Furthermore, to adaptively fuse features in both the frequency domain and spatial domain,we design a Spatial-frequency Information Dynamic Fusion (SIDF) module to dynamically allocate weights. Finally, we modify the network from a regression model to a classification model to speed up convergence and improve the accuracy of the algorithm. The experiment results show that the accuracy of the proposed method is higher than 98% on clean images. Meanwhile, in robust environments, the algorithm proposed maintains an average accuracy of over 81%.
References
[1]
2017. NRCS Photo Gallery. Website. http://photogallery.nrcs.usda.gov.
[2]
Riza Alp Guler, George Trigeorgis, Epameinondas Antonakos, Patrick Snape, Stefanos Zafeiriou, and Iasonas Kokkinos. 2017. Densereg: Fully convolutional dense shape regression in-the-wild. In Proceedings of the IEEE conference on computer vision and pattern recognition. 6799--6808.
[3]
Tiziano Bianchi and Alessandro Piva. 2012. Image forgery localization via block-grained analysis of JPEG artifacts. IEEE Transactions on Information Forensics Security, Vol. 7, 3 (2012), 1003--1017.
[4]
Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. 2020. End-to-end object detection with transformers. In European conference on computer vision. Springer, 213--229.
[5]
Kaimeng Chen, Qingxiao Guan, Weiming Zhang, and Nenghai Yu. 2023. Reversible data hiding in encrypted images based on binary symmetric channel model and polar code. IEEE Transactions on Dependable and Secure Computing, Vol. 20, 6 (2023), 4519--4535.
[6]
Xin Cheng, Jinwei Wang, Hao Wang, Xiangyang Luo, and Bin Ma. 2024. Quantization step estimation of color images based on Res2Net-C with frequency clustering prior knowledge. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 34, 1 (2024), 632--646.
[7]
Duc-Tien Dang-Nguyen, Cecilia Pasquini, Valentina Conotter, and Giulia Boato. 2015. RAISE: A raw images dataset for digital image forensics. In Proceedings of the 6th ACM multimedia systems conference. 219--224.
[8]
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020).
[9]
Zhigang Fan and Ricardo L De Queiroz. 2003. Identification of bitmap compression history: JPEG detection and quantizer estimation. IEEE Transactions on Image Processing, Vol. 12, 2 (2003), 230--235.
[10]
Jessica Fridrich, Miroslav Goljan, and Rui Du. 2001. Steganalysis based on JPEG compatibility. In Multimedia Systems and Applications IV, Vol. 4518. 275--280.
[11]
Fausto Galvan, Giovanni Puglisi, Arcangelo Ranieri Bruna, and Sebastiano Battiato. 2014. First quantization matrix estimation from double compressed JPEG images. IEEE Transactions on Information Forensics Security, Vol. 9, 8 (2014), 1299--1310.
[12]
Qingxiao Guan, Kaimeng Chen, Hefeng Chen, Weiming Zhang, and Nenghai Yu. 2022. Detecting steganography in JPEG images recompressed with the same quantization matrix. IEEE Transactions on information Forensics Security, Vol. 32, 9 (2022), 6002--6016.
[13]
Bin Li, Tian-Tsong Ng, Xiaolong Li, Shunquan Tan, and Jiwu Huang. 2015. Statistical model of JPEG noises and its application in quantization step estimation. IEEE Transactions on Image Processing, Vol. 24, 5 (2015), 1471--1484.
[14]
Wenjie Li, Xiaolong Li, Rongrong Ni, and Yao Zhao. 2021. Quantization step estimation for JPEG image forensics. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32, 7 (2021), 4816--4827.
[15]
Guo-Shiang Lin, Min-Kuan Chang, and You-Lin Chen. 2011. A passive-blind forgery detection scheme based on content-adaptive quantization table estimation. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 21, 4 (2011), 421--434.
[16]
Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision. 10012--10022.
[17]
Jan Lukáš and Jessica Fridrich. 2003. Estimation of primary quantization matrix in double compressed JPEG images. In Proc. Digital forensic research workshop. 5--8.
[18]
Weiqi Luo, Jiwu Huang, and Guoping Qiu. 2010. JPEG error analysis and its applications to digital image forensics. IEEE Transactions on Information Forensics Security, Vol. 5, 3 (2010), 480--491.
[19]
Bin Ma and Yun Q Shi. 2016. A reversible data hiding scheme based on code division multiplexing. IEEE Transactions on information Forensics Security, Vol. 11, 9 (2016), 1914--1927.
[20]
David Megías and Daniel Lerch-Hostalot. 2022. Subsequent embedding in targeted image steganalysis: Theoretical framework and practical applications. IEEE Transactions on Dependable and Secure Computing, Vol. 20, 2 (2022), 1403--1421.
[21]
Ramesh Neelamani, Ricardo De Queiroz, Zhigang Fan, Sanjeeb Dash, and Richard G Baraniuk. 2006. JPEG compression history estimation for color images. IEEE Transactions on Image Processing, Vol. 15, 6 (2006), 1365--1378.
[22]
Yakun Niu, Xiaolong Li, Yao Zhao, and Rongrong Ni. 2021. Detection of double JPEG compression with the same quantization matrix via convergence analysis. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32, 5 (2021), 3279--3290.
[23]
Yakun Niu, Benedetta Tondi, Yao Zhao, and Mauro Barni. 2019. Primary quantization matrix estimation of double compressed JPEG images via CNN. IEEE Signal Processing Letters, Vol. 27 (2019), 191--195.
[24]
Yakun Niu, Benedetta Tondi, Yao Zhao, Rongrong Ni, and Mauro Barni. 2021. Image splicing detection, localization and attribution via JPEG primary quantization matrix estimation and clustering. IEEE Transactions on Information Forensics Security, Vol. 16 (2021), 5397--5412.
[25]
Tomas Pevny and Jessica Fridrich. 2008. Detection of double-compression in JPEG images for applications in steganography. IEEE Transactions on Information Forensics Security, Vol. 3, 2 (2008), 247--258.
[26]
Tong Qiao, Xiangyang Luo, Ting Wu, Ming Xu, and Zhenxing Qian. 2019. Adaptive steganalysis based on statistical model of quantized DCT coefficients for JPEG images. IEEE Transactions on Dependable and Secure Computing, Vol. 18, 6 (2019), 2736--2751.
[27]
Gerald Schaefer and Michal Stich. 2003. UCID: An uncompressed color image database. In Storage and Retrieval Methods and Applications for Multimedia 2004, Vol. 5307. SPIE, 472--480.
[28]
Thanh Hai Thai, Rémi Cogranne, Florent Retraint, et al. 2016. JPEG quantization step estimation and its applications to digital image forensics. IEEE Transactions on Information Forensics Security, Vol. 12, 1 (2016), 123--133.
[29]
Benedetta Tondi, Andrea Costanzo, Dequ Huang, and Bin Li. 2021. Boosting CNN-based primary quantization matrix estimation of double JPEG images via a classification-like architecture. EURASIP Journal on Information Security, Vol. 2021, 1 (2021), 1--14.
[30]
Hao Wang, Jinwei Wang, Xiangyang Luo, Yuhui Zheng, Bin Ma, Jinsheng Sun, and Sunil Kr Jha. 2021. Detecting aligned double JPEG compressed color image with same quantization matrix based on the stability of image. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 32, 6 (2021), 4065--4080.
[31]
Hao Wang, Jinwei Wang, Jiawei Zhang, Xiangyang Luo, Bin Ma, Bin Li, and Jinsheng Sun. 2024. General Forensics for Aligned Double JPEG Compression Based on the Quantization Interference. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 34, 6 (2024), 5191--5206.
[32]
Jinwei Wang, Hao Wang, Jian Li, Xiangyang Luo, Yun-Qing Shi, and Sunil Kumar Jha. 2019. Detecting double JPEG compressed color images with the same quantization matrix in spherical coordinates. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 30, 8 (2019), 2736--2749.
[33]
Fei Xue, Ziyi Ye, Wei Lu, Hongmei Liu, and Bin Li. 2017. Mse period based estimation of first quantization step in double compressed JPEG images. Signal Processing: Image Communication, Vol. 57 (2017), 76--83.
[34]
Jianquan Yang, Yulan Zhang, Guopu Zhu, and Sam Kwong. 2020. A clustering-based framework for improving the performance of JPEG quantization step estimation. IEEE Transactions on Circuits and Systems for Video Technology, Vol. 31, 4 (2020), 1661--1672.
[35]
Jianquan Yang, Guopu Zhu, Jiwu Huang, and Xi Zhao. 2015. Estimating JPEG compression history of bitmaps based on factor histogram. Digital Signal Processing, Vol. 41 (2015), 90--97.
[36]
Zijin Yang, Kejiang Chen, Kai Zeng, Weiming Zhang, and Nenghai Yu. 2024. Provably Secure Robust Image Steganography. IEEE Transactions on Multimedia, Vol. 26 (2024), 5040--5053.
[37]
Heng Yao, Hongbin Wei, Tong Qiao, and Chuan Qin. 2020. JPEG quantization step estimation with coefficient histogram and spectrum analyses. Journal Of Visual Communication And Image Representation, Vol. 69 (2020), 102795.
[38]
Shuiming Ye, Qibin Sun, and Ee-Chien Chang. 2007. Detecting digital image forgeries by measuring inconsistencies of blocking artifact. In 2007 IEEE International Conference on Multimedia and Expo. Ieee, 12--15.
[39]
Liyang Yu, Qi Han, Xiamu Niu, SM Yiu, Junbin Fang, and Ye Zhang. 2016. An improved parameter estimation scheme for image modification detection based on DCT coefficient analysis. Forensic Science International, Vol. 259 (2016), 200--209.
[40]
Jiansong Zhang, Kejiang Chen, Chuan Qin, Weiming Zhang, and Nenghai Yu. 2024. AAS: Automatic Virtual Data Augmentation for Deep Image Steganalysis. IEEE Transactions on Dependable and Secure Computing, Vol. 21, 4 (2024), 3515--3527.
[41]
Yi Zhang, Chuan Qin, Weiming Zhang, Fenlin Liu, and Xiangyang Luo. 2018. On the fault-tolerant performance for a class of robust image steganography. Signal Processing, Vol. 146 (2018), 99--111.
Index Terms
- Advancing Quantization Steps Estimation: A Two-Stream Network Approach for Enhancing Robustness
Recommendations
MBRS: Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression
MM '21: Proceedings of the 29th ACM International Conference on MultimediaBased on the powerful feature extraction ability of deep learning architecture, recently, deep-learning based watermarking algorithms have been widely studied. The basic framework of such algorithm is the auto-encoder like end-to-end architecture with ...
First quantization matrix estimation for double compressed JPEG images utilizing novel DCT histogram selection strategy
ICVGIP '16: Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image ProcessingThe Double JPEG problem in image forensics has been gaining importance since it involves two compression cycles and there is a possibility of tampering having taken place after the first cycle thereby calling for accurate methods to detect and localize ...
Robust image hiding network with Frequency and Spatial Attentions
AbstractConvert Image Communication (CIC) is a promising technology to protect the privacy of images. Recently, the emergence of robust CIC resistant to JPEG compression has gained due to the widespread use of JPEG compression in image communication. ...
Highlights- We use frequency domain to capture the intrinsic DCT changing in JPEG compression.
- Multi-attentions are derived based on compression affect and the human visual system.
- Experiments show high image quality and resilience to JPEG ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
October 2024
11719 pages
ISBN:9798400706868
DOI:10.1145/3664647
- General Chairs:
- Jianfei Cai,
- Mohan Kankanhalli,
- Balakrishnan Prabhakaran,
- Susanne Boll,
- Program Chairs:
- Ramanathan Subramanian,
- Liang Zheng,
- Vivek K. Singh,
- Pablo Cesar,
- Lexing Xie,
- Dong Xu
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 28 October 2024
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- National Key R and D Program of China
- Zhongyuan Science and Technology Innovation Leading Talent Project of China
- Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness
- National Natural Science Foundation of China
- the Graduate Student Scientific Research Innovation Projects of Jiangsu Province
Conference
MM '24
Sponsor:
MM '24: The 32nd ACM International Conference on Multimedia
October 28 - November 1, 2024
Melbourne VIC, Australia
Acceptance Rates
MM '24 Paper Acceptance Rate 1,150 of 4,385 submissions, 26%;
Overall Acceptance Rate 2,145 of 8,556 submissions, 25%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 23Total Downloads
- Downloads (Last 12 months)23
- Downloads (Last 6 weeks)23
Reflects downloads up to 11 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in