Abstract
Automatic localization of tampered regions of a JPEG image has attracted lots of attention in recent times. It is known that the statistical signatures of single and Double JPEG (DJPEG) compression are distinct, and the presence of both the signatures inside an image is proof of manipulation. Automatic localization of tampered regions is carried out by segregating the singly and doubly compressed regions of an image. However, the robustness of the localization process is questionable as very few attempts are made to highlight their vulnerabilities. Here, we propose an adversarial framework, known as jForge, through which one can create a DJPEG compressed image that only bears the signatures of a single compression, and it renders the localization process ineffective. jForge removes the footprints of JPEG compression using model-based approximation techniques. Arguably, this is the first successful attempt to model the DC coefficients of an image, and it employs polynomial regression of two variables to accomplish the same. Similarly, AC coefficients have been approximated using low degree polynomials. We have mounted jForge on three popular forgery localization schemes, and none of them is effective against it. This raises serious doubt regarding the efficacy of the statistical signature-based paradigm of forgery localization.
Similar content being viewed by others
References
alZahir S, Hammad R (2020) Image forgery detection using image similarity. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-09502-4
Barni M, Fontani M, Tondi B (2015) Universal counterforensics of multiple compressed jpeg images. In: Shi YQ, Kim HJ, Pérez-González F, Yang CN (eds) Digital-Forensics and Watermarking. Springer International Publishing, Cham, pp 31–46
Barni M, Stamm MC, Tondi B (2018) Adversarial multimedia forensics: Overview and challenges ahead. In: 2018 26th European signal processing conference (EUSIPCO), pp 962–966
Bhaduri Mandal A, Das TK (2019) Anti-forensics of a nad-jpeg detection scheme using estimation of dc coefficients. In: Proceedings of information systems security - 15th international conference, ICISS 2019, Hyderabad, India, December 16-20, 2019, Lecture Notes in Computer Science, vol 11952. Springer International Publishing, pp 307–323
Bhardwaj D, Pankajakshan V (2018) A jpeg blocking artifact detector for image forensics. Signal Process Image Commun 68:155–161
Bianchi T, Piva A (2012) Detection of nonaligned double jpeg compression based on integer periodicity maps. IEEE Trans Inf Forensics Secur 7(2):842–848
Bianchi T, Piva A (2012) Image forgery localization via block-grained analysis of jpeg artifacts. IEEE Trans Inf Forensics Secur 7(3):1003–1017
Chen Z, Zhao Y, Ni R (2017) Detection of operation chain: Jpeg-resampling-jpeg. Signal Process Image Commun 57:8–20
Chu X, Stamm MC, Chen Y, Liu KJR (2015) On antiforensic concealability with rate-distortion tradeoff. IEEE Trans Image Process 24(3):1087–1100
Cristin R, Ananth JP, Cyril Raj V (2018) Illumination-based texture descriptor and fruitfly support vector neural network for image forgery detection in face images. IET Image Process 12(8):1439–1449
Dalmia N, Okade M (2018) Robust first quantization matrix estimation based on filtering of recompression artifacts for non-aligned double compressed jpeg images. Signal Process Image Commun 61:9–20
Das TK (2018) Anti-forensics of jpeg compression detection schemes using approximation of dct coefficients. Multimed Tools Appl 77(24):31835–31854
Das TK, Maitra S (2004) Cryptanalysis of correlation-based watermarking schemes using single watermarked copy. IEEE Signal Process Lett 11 (4):446–449
Fahmy G, Alqallaf A, Wurtz R (2015) Phase based detection of jpeg counter forensics. In: 2015 IEEE International conference on electronics, circuits, and systems (ICECS), pp 37–40
Fan W, Wang K, Cayre F, Xiong Z (2014) Jpeg anti-forensics with improved tradeoff between forensic undetectability and image quality. IEEE Trans Inf Forensics Secur 9(8):1211–1226
Fan Z, de Queiroz RL (2003) Identification of bitmap compression history: Jpeg detection and quantizer estimation. IEEE Trans Image Process 12 (2):230–235
Farid H (2009) Exposing digital forgeries from jpeg ghosts. IEEE Trans Inf Forensics Secur 4(1):154–160
Farooq S, Yousaf MH, Hussain F (2017) A generic passive image forgery detection scheme using local binary pattern with rich models. Comput Electr Eng 62:459–472
Huang F, Huang J, Shi YQ (2010) Detecting double jpeg compression with the same quantization matrix. IEEE Trans Inf Forensics Secur 5(4):848–856
Huang HY, Ciou AJ (2019) Copy-move forgery detection for image forensics using the superpixel segmentation and the helmert transformation. EURASIP J Image Video Process 2019(1):68
Jaiprakash SP, Desai MB, Prakash CS, Mistry VH, Radadiya KL (2020) Low dimensional dct and dwt feature based model for detection of image splicing and copy-move forgery. Multimed Tools Appl. https://doi.org/10.1007/s11042-020-09415-2
Korus P (2017) Digital image integrity – a survey of protection and verification techniques. Digital Signal Processing 71:1–26
Lai S, Böhme R (2011) Countering counter-forensics: The case of jpeg compression. In: Information Hiding: 13th International Conference, IH 2011, Prague, Czech Republic, May 18-20, 2011, Revised Selected Papers. Springer, Berlin, pp 285–298
Li B, Ng T, Li X, Tan S, Huang J (2015) Revealing the trace of high-quality jpeg compression through quantization noise analysis. IEEE Trans Inf Forensics Secur 10(3):558–573
Li H, Luo W, Huang J (2015) Anti-forensics of double jpeg compression with the same quantization matrix. Multimed Tools Appl 74(17):6729–6744
Li H, Luo W, Qiu X, Huang J (2018) Identification of various image operations using residual-based features. IEEE Trans Circuits Sys Video Technol 28(1):31–45
Lin Z, He J, Tang X, Tang CK (2009) Fast, automatic and fine-grained tampered jpeg image detection via dct coefficient analysis. Pattern Recogn 42(11):2492–2501
Lukáš J, Fridrich J (2003) Estimation of primary quantization matrix in double compressed jpeg images. In: Proc. of DFRWS
Luo W, Huang J, Qui G (2010) Jpeg error analysis and its applications to digital image forensics. IEEE Trans Inf Forensics Secur 5(3):480–491
Mayer O, Stamm MC (2020) Forensic similarity for digital images. IEEE Trans Inf Forensics Secur 15:1331–1346
Milani S, Tagliasacchi M, Tubaro S (2012) Discriminating multiple jpeg compression using first digit features. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 2253–2256
Nasiri M, Behrad A (2019) Using expectation-maximization for exposing image forgeries by revealing inconsistencies in shadow geometry. J Vis Commun Image Represent 58:323–333
Niu Y, Li X, Zhao Y, Ni R (2019) An enhanced approach for detecting double jpeg compression with the same quantization matrix. Signal Process Image Commun 76:89–96
Pevny T, Fridrich J (2008) Detection of double-compression in jpeg images for applications in steganography. IEEE Trans Inf Forensics Secur 3(2):247–258
Qazi T, Hayat K, Khan SU, Madani SA, Khan IA, Kołodziej J, Li H, Lin W, Yow KC, Xu CZ (2013) Survey on blind image forgery detection. IET Image Processing 7(7):660–670
Sallee P (2004) Matlab jpeg toolbox. http://www.philsallee.com/jpegtbx/index.html
Schaefer G, Stich M (2003) UCID: an uncompressed color image database. In: Yeung MM, Lienhart RW, Li CS (eds) Storage and retrieval methods and applications for multimedia 2004, vol 5307, pp 472–480
Singh G, Singh K (2017) Improved jpeg anti-forensics with better image visual quality and forensic undetectability. Forensic Sci Int 277:133–147
Stamm MC, Liu KJR (2011) Anti-forensics of digital image compression. IEEE Trans Inf Forensics Secur 6(3):1050–1065
Stamm MC, Tjoa SK, Lin WS, Liu KJR (2010) Anti-forensics of jpeg compression. In: 2010 IEEE International conference on acoustics, speech and signal processing, pp 1694–1697
Taimori A, Razzazi F, Behrad A, Ahmadi A, Babaie-Zadeh M (2016) Quantization-unaware double jpeg compression detection. J Math Imaging Vis 54(3):269–286
Uehara T, Safavi-Naini R, Ogunbona P (2006) Recovering dc coefficients in block-based dct. IEEE Trans Image Process 15(11):3592–3596
Valenzise G, Nobile V, Tagliasacchi M, Tubaro S (2011) Countering jpeg anti-forensics. In: 2011 18th IEEE international conference on image processing, pp 1949–1952
Wang W, Dong J, Tan T (2014) Exploring dct coefficient quantization effects for local tampering detection. IEEE Trans Inf Forensics Secur 9 (10):1653–1666
Wei W, Sun L, Tang D, Zhao Y, Li H (2012) A survey of passive image forensics. In: Lei J, Wang FL, Li M, Luo Y (eds) Network computing and information security. Springer, Berlin, pp 45–55
Yang J, Zhu G, Huang J, Zhao X (2015) Estimating jpeg compression history of bitmaps based on factor histogram. Digital Signal Processing 41:90–97
Yerushalmy I, Hel-Or H (2011) Digital image forgery detection based on lens and sensor aberration. Int J Comput Vis 92(1):71–91
Zheng L, Zhang Y, Thing VL (2019) A survey on image tampering and its detection in real-world photos. J Vis Commun Image Represent 58:380–399
Zhu N, Li Z (2018) Blind image splicing detection via noise level function. Signal Process Image Commun 68:181–192
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work is a thoroughly revised and extended version of [4]. Section 3.2 of this paper introduces an improved approximation algorithm for AC coefficients of a JPEG image, and it is an addition over the conference version.
Rights and permissions
About this article
Cite this article
Bhaduri Mandal, A., Das, T.K. jForge: An adversarial method to deceive JPEG forgery localization schemes. Multimed Tools Appl 81, 22807–22832 (2022). https://doi.org/10.1007/s11042-021-11265-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11265-5