The week's pick
Reseach Article
An Adversarial Technique for Removal of JPEG Ghosts
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 10 |
| Year of Publication: 2024 |
| Authors: Arkaprava Bhaduri Mandal, Deepak Agnihotri, Tanmoy Kanti Das |
10.5120/ijca2024923448
|
Arkaprava Bhaduri Mandal, Deepak Agnihotri, Tanmoy Kanti Das . An Adversarial Technique for Removal of JPEG Ghosts. International Journal of Computer Applications. 186, 10 ( Feb 2024), 1-8. DOI=10.5120/ijca2024923448
Abstract
The presence of statistical signatures of both double and single JPEG compression in an image indicates its maliciousness, and several techniques have been proposed using this fact to detect tempered images. One such statistical signature is known as JPEG ghosts where the presence of minima and local minima in the DCT coefficients of a JPEG image proves the existence of double JPEG compression. Moreover, it can localize the double JPEG compression quite successfully. However, this paper presents an adversarial method that can erase the statistical signature of the double JPEG compression without affecting the visual quality of the image. The proposed adversarial technique approximates the DCT coefficients using low-degree polynomials in such a way that no trace of prior JPEG compression can be detected. The transformed DCT coefficients exhibit statistical properties that are similar to uncompressed images. This technique successfully defeats the JPEG ghost-based forensic detection and localization method which raises serious concern regarding the robustness of the existing forensics schemes based on the JPEG artifacts.
References
- Beijing Chen, Weijin Tan, Gouenou Coatrieux, Yuhui Zheng, and Yun-Qing Shi. A serial image copy-move forgery localization scheme with source/target distinguishment. IEEE Transactions on Multimedia, 23:3506–3517, 2021.
- Xiaoyu Chu, Matthew Christopher Stamm, Yan Chen, and KJ Ray Liu. On antiforensic concealability with ratedistortion tradeoff. IEEE Transactions on Image Processing, 24(3):1087–1100, 2015.
- William Jay Conover. Practical nonparametric statistics. 1980.
- Nandita Dalmia and Manish Okade. Robust first quantization matrix estimation based on filtering of recompression artifacts for non-aligned double compressed jpeg images. Signal Processing: Image Communication, 61:9 – 20, 2018.
- T. K. Das and S. Maitra. Cryptanalysis of correlation-based watermarking schemes using single watermarked copy. IEEE Signal Processing Letters, 11(4):446–449, April 2004.
- T. K. Das, S. Maitra, and J. Mitra. Cryptanalysis of optimal differential energy watermarking (DEW) and a modified robust scheme. IEEE Trans. Signal Processing, 53(2-2):768– 775, 2005.
- Tanmoy Kanti Das. Anti-forensics of jpeg compression detection schemes using approximation of dct coefficients. Multimedia Tools and Applications, Jun 2018.
- Feng Ding, Yuxi Shi, Guopu Zhu, and Yun-Qing Shi. Smoothing identification for digital image forensics. Multimedia Tools and Applications, Nov 2018.
- Wei Fan, Kai Wang, Francois Cayre, and Zhang Xiong. Jpeg anti-forensics with improved tradeoff between forensic undetectability and image quality. IEEE Transactions on Information Forensics and Security, 9(8):1211–1226, 2014.
- Wei Fan, Kai Wang, Franc¸ois Cayre, and Zhang Xiong. Median filtered image quality enhancement and anti-forensics via variational deconvolution. IEEE transactions on information forensics and security, 10(5):1076–1091, 2015.
- Z. Fan and R. L. de Queiroz. Identification of bitmap compression history: Jpeg detection and quantizer estimation. IEEE Transactions on Image Processing, 12(2):230–235, Feb 2003.
- Hany Farid. Exposing digital forgeries from jpeg ghosts. Trans. Info. For. Sec., 4(1):154–160, March 2009.
- Fangjun Huang, Jiwu Huang, and Yun Qing Shi. Detecting double jpeg compression with the same quantization matrix. IEEE Transactions on Information Forensics and Security, 5(4):848–856, 2010.
- Hui-Yu Huang and Ai-Jhen Ciou. Copy-move forgery detection for image forensics using the superpixel segmentation and the helmert transformation. EURASIP Journal on Image and Video Processing, 2019(1):68, Jun 2019.
- Sharanjit Kaur and Manpreet Kaur. Novel method for copymove forgery detection. International Journal of Computer Applications, 174(18):10–14, Feb 2021.
- Dohyun Kim, Wonhyuk Ahn, and Heung-Kyu Lee. End-toend anti-forensics network of single and double jpeg detection. IEEE Access, 9:13390–13402, 2021.
- Amit Kumar, Ankush Kansal, and Kulbir Singh. Anti-forensic approach for jpeg compressed images with enhanced image quality and forensic undetectability. Multimedia Tools and Applications, 79:8061–8084, 2020.
- Chothmal Kumawat and Vinod Pankajakshan. A robust jpeg compression detector for image forensics. Signal Processing: Image Communication, 89:116008, 2020.
- Thuong Le-Tien, Tu Huynh-Kha, Long Pham-Cong-Hoan, An Tran-Hong, Nilanjan Dey, and Marie Luong. Combined zernike moment and multiscale analysis for tamper detection in digital images. Informatica, 41(1), 2017.
- Haodong Li, Weiqi Luo, and Jiwu Huang. Anti-forensics of double jpeg compression with the same quantization matrix. Multimedia Tools Appl., 74(17):6729–6744, September 2015.
- Yuanman Li and Jiantao Zhou. Anti-forensics of lossy predictive image compression. IEEE Signal Processing Letters, 22(12):2219–2223, 2015.
- Ocha Maulidya and Imam Riadi. Image forensics to detect image authenticity using error level analysis and noise analysis methods. International Journal of Computer Applications, 185(28):6–11, Aug 2023.
- Morteza Nasiri and Alireza Behrad. Using expectationmaximization for exposing image forgeries by revealing inconsistencies in shadow geometry. Journal of Visual Communication and Image Representation, 58:323 – 333, 2019.
- Yakun Niu, Xiaolong Li, Yao Zhao, and Rongrong Ni. An enhanced approach for detecting double jpeg compression with the same quantization matrix. Signal Processing: Image Communication, 76:89–96, 2019.
- Zhenxing Qian and Xinpeng Zhang. Improved anti-forensics of jpeg compression. Journal of Systems and Software, 91:100–108, 2014.
- Phil Sallee. Matlab jpeg toolbox, 2003.
- Gerald Schaefer and Michal Stich. Ucid: An uncompressed color image database. In Storage and Retrieval Methods and Applications for Multimedia 2004, volume 5307, pages 472– 481. International Society for Optics and Photonics, 2003.
- Gurinder Singh and Kulbir Singh. Improved jpeg antiforensics with better image visual quality and forensic undetectability. Forensic Science International, 277:133–147, 2017.
- Matthew C Stamm and KJ Ray Liu. Anti-forensics of digital image compression. IEEE Transactions on Information Forensics and Security, 6(3):1050–1065, 2011.
- Diaa Uliyan, Mohammad AM Abushariah, and Ahmad Mousa Altamimi. Blur invariant features for exposing region duplication forgery using anms and local phase quantization. Informatica, 42(4), 2018.
- JinweiWang,Wei Huang, Xiangyang Luo, Yun-Qing Shi, and Sunil Kr Jha. Non-aligned double jpeg compression detection based on refined markov features in qdct domain. Journal of Real-Time Image Processing, 17(1):7–16, 2020.
- Peiyu Zhuang, Haodong Li, Shunquan Tan, Bin Li, and Jiwu Huang. Image tampering localization using a dense fully convolutional network. IEEE Transactions on Information Forensics and Security, 16:2986–2999, 2021.
Index Terms
Keywords