Published July 6, 2023 | Version v1
Conference paper Open

JADE OWL: JPEG 2000 forensics by wavelet offset consistency analysis

Creators

  • 1. Université Paris Saclay, ENS Paris Saclay, CNRS, Centre Borelli, France

Description

In a world teeming with digital images, the credibility of visual data has become of paramount importance. While it is now simpler than ever to manipulate an image for malicious purposes such as misinformation, the tools for detecting such alterations have predominantly been developed for either uncompressed or JPEG-compressed natural images. However, medical and satellite imagery, domains where the potential for fraud is high, often use a different compression format -- JPEG 2000.
We present a JPEG 2000 Anomaly Detection Estimator via Offset of Wavelet Localization -- the Jade Owl --, a novel method for detecting forgeries in JPEG 2000 images by analyzing the consistency of traces left by its compression. Our technique hinges on the premise that the wavelet coefficients of a JPEG 2000 image are lower when the same offset is applied during the wavelet transform than they are when the offset is different. By employing this principle locally, we're able to detect regions with significantly different offsets, indicating potential forgeries such as copy-move. An accompanying \textit{a contrario} model further refines this detection to make automatic detections while controlling false positives. To evaluate the method, we've created a unique dataset of JPEG 2000 forgeries. This novel approach significantly paves the way for JPEG 2000 image forensics, introducing a sensitive and efficient tool for authenticity verification in critical sectors such as healthcare and satellite imagery.

Notes

This work has received funding by the European Union under the Horizon Europe vera.ai project, grant agreement number 101070093, and by the ANR under the APATE project, grant number ANR-22-CE39-0016. Centre Borelli is also a member of Université Paris Cité, SSA and INSERM.

Files

JADE_OWL-5.pdf

Files (15.5 MB)

Name Size Download all
md5:85336508dc2644f2bbeb2d7ff7e14815
15.5 MB Preview Download

Additional details

Funding

vera.ai – vera.ai: VERification Assisted by Artificial Intelligence 101070093
European Commission
APATE – A Prototype deepfake Assessment Toolbox for forensic Experts ANR-22-CE39-0016
Agence Nationale de la Recherche

References

  • A. Ghoneim, G. Muhammad, S. U. Amin, and B. Gupta, "Medical image forgery detection for smart healthcare," IEEE Communications Magazine, vol. 56, no. 4, pp. 33–37, 2018.
  • C.-R. Piao, D.-M. Woo, D.-C. Park, and S.-S. Han, "Medical image authentication using hash function and integer wavelet transform," in 2008 Congress on Image and Signal Processing, vol. 1. IEEE, 2008, pp. 7–10.
  • C. Gudavalli, E. Rosten, L. Nataraj, S. Chandrasekaran, and B. S. Manjunath, "Seetheseams: Localized detection of seam carving based image forgery in satellite imagery," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Work- shops, June 2022, pp. 1–11.
  • J. Horváth, D. Güera, S. K. Yarlagadda, P. Bestagini, F. M. Zhu, S. Tubaro, and E. J. Delp, "Anomaly-based manipulation detection in satellite images," networks, vol. 29, p. 21, 2019.
  • Q. Bammey, R. G. von Gioi, and J.-M. Morel, "An adaptive neural net- work for unsupervised mosaic consistency analysis in image forensics," in CVPR, 2020.
  • Q. Bammey, R. G. von Gioi, and J.-M. Morel, "Forgery detection by internal positional learning of demosaicing traces," in WACV, January 2022, pp. 328–338.
  • M. Gardella, P. Musé, J.-M. Morel, and M. Colom, "Noisesniffer: a fully automatic image forgery detector based on noise analysis," in IWBF. IEEE, 2021.
  • T. Nikoukhah, J. Anger, T. Ehret, M. Colom, J.-M. Morel, and R. Grompone von Gioi, "JPEG grid detection based on the number of DCT zeros and its application to automatic and localized forgery detection," in CVPRW, 2019.
  • Y. Wu, W. AbdAlmageed, and P. Natarajan, "Mantra-net: Manipulation tracing network for detection and localization of image forgeries with anomalous features," in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  • D. Cozzolino and L. Verdoliva, "Noiseprint: A cnn-based camera model fingerprint," IEEE TIFS, 2020.
  • S. Manimurugan and K. Porkumaran, "A new fast and efficient visual cryptography scheme for medical images with forgery detection," in 2011 International Conference on Emerging Trends in Electrical and Computer Technology, 2011, pp. 594–599.
  • H. Farid, "Exposing digital forgeries from jpeg ghosts," IEEE Transac- tions on Information Forensics and Security, vol. 4, no. 1, pp. 154–160, 2009.
  • G. Ulutas, A. Ustubioglu, B. Ustubioglu, V. V Nabiyev, and M. Ulutas, "Medical image tamper detection based on passive image authentica- tion," Journal of digital imaging, vol. 30, pp. 695–709, 2017.
  • D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International journal of computer vision, vol. 60, pp. 91–110, 2004.
  • G. Qadir, X. Zhao, and A. T. Ho, "Estimating jpeg2000 compression for image forensics using benford's law," in Optics, Photonics, and Digital Technologies for Multimedia Applications, vol. 7723. SPIE, 2010, pp. 133–142.
  • J. Zhang, H. Wang, and Y. Su, "Detection of double-compression in jpeg2000 images for application in image forensics." Journal of multimedia, vol. 4, no. 6, 2009.
  • A. Desolneux, L. Moisan, and J. Morel, "From gestalt theory to image analysis. interdisciplinary applied mathematics, vol. 35," pp. 7–23, Oct 2007. [Online]. Available: https://doi.org/10.1023/A:1026593302236
  • A. Desolneux, L. Moisan, and J.-M. Morel, "Meaningful alignments," IJCV, 2000.
  • P. Moulon, P. Monasse, and R. Marlet, "Adaptive structure from motion with a contrario model estimation," in Computer Vision – ACCV 2012, K. M. Lee, Y. Matsushita, J. M. Rehg, and Z. Hu, Eds., Berlin, Heidelberg, 2013.
  • A. Davy, T. Ehret, J.-M. Morel, and M. Delbracio, "Reducing anomaly detection in images to detection in noise," in IEEE ICIP, 2018.
  • A. Robin, L. Moisan, and S. Le Hegarat-Mascle, "An a-contrario approach for subpixel change detection in satellite imagery," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, 2010.
  • T. Ehret, A. Davy, M. Delbracio, and J.-M. Morel, "How to Reduce Anomaly Detection in Images to Anomaly Detection in Noise," Image Processing On Line, vol. 9, 2019.
  • T. Dagobert, R. Grompone von Gioi, C. de Franchis, J.-M. Morel, and C. Hessel, "Cloud Detection by Luminance and Inter-band Parallax Analysis for Pushbroom Satellite Imagers," Image Processing On Line, vol. 10, 2020.
  • L. Moisan, P. Moulon, and P. Monasse, "Automatic Homographic Registration of a Pair of Images, with A Contrario Elimination of Outliers," Image Processing On Line, vol. 2, 2012.
  • N. Mandroux, T. Dagobert, S. Drouyer, and R. Grompone von Gioi, "Single Date Wind Turbine Detection on Sentinel-2 Optical Images," Image Processing On Line, vol. 12, 2022.
  • A. Buades, R. Grompone von Gioi, and J. Navarro, "Contours, Corners and T-Junctions Detection Algorithm," Image Processing On Line, vol. 8, 2018.
  • C. Aguerrebere, P. Sprechmann, P. Muse, and R. Ferrando, "A-contrario localization of epileptogenic zones in spect images," in 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, 2009.
  • E. Aldea and S. L. Hégarat-Mascle, "Robust crack detection for un- manned aerial vehicles inspection in an a-contrario decision framework," JEI, 2015.
  • R. Grompone von Gioi, C. Hessel, T. Dagobert, J.-M. Morel, and C. de Franchis, "Ground Visibility in Satellite Optical Time Series Based on A Contrario Local Image Matching," Image Processing On Line, vol. 11, 2021.
  • R. Grompone von Gioi, J. Jakubowicz, J.-M. Morel, and G. Randall, "Lsd: A fast line segment detector with a false detection control," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, 2010.
  • R. Grompone von Gioi, J. Jakubowicz, J.-M. Morel, and G. Randall, "LSD: a Line Segment Detector," IPOL, vol. 2, pp. 35–55, 2012. [32] R. Grompone von Gioi and G. Randall, "Unsupervised Smooth Contour Detection," Image Processing On Line, vol. 6, 2016.
  • A. Gómez, G. Randall, and R. Grompone von Gioi, "A Contrario 3D Point Alignment Detection Algorithm," Image Processing On Line, vol. 7, 2017.
  • X. Huang, W. Yang, H. Zhang, and G.-S. Xia, "Automatic ship detection in sar images using multi-scale heterogeneities and an a contrario decision," Remote Sensing, 2015.
  • J. Lezama, G. Randall, J.-M. Morel, and R. Grompone von Gioi, "An Unsupervised Point Alignment Detection Algorithm," Image Processing On Line, vol. 5, 2015.
  • J.-L. Lisani and S. Ramis, "A Contrario Detection of Faces with a Short Cascade of Classifiers," Image Processing On Line, vol. 9, 2019.
  • J.-L. Lisani, S. Ramis, and F. J. Perales, "A contrario detection of faces: A case example," SIAM Journal on Imaging Sciences, vol. 10, 2017.
  • Q. Bammey, "A contrario mosaic analysis for image forensics," in Ad- vanced Concepts for Intelligent Vision Systems, ACIVS 2023. Springer, Aug. 2023.
  • Q. Bammey, R. G. v. Gioi, and J.-M. Morel, "Reliable demosaicing detection for image forensics," in 27th European Signal Processing Conference (EUSIPCO), 2019, pp. 1–5.
  • Q. Bammey, R. Grompone Von Gioi, and J.-M. Morel, "Demosaicing to detect demosaicing and image forgeries," in 2022 IEEE International Workshop on Information Forensics and Security (WIFS), 2022, pp. 1–6.
  • Y. Li, M. Gardella, Q. Bammey, T. Nikoukhah, J.-M. Morel, M. Colom, and R. Grompone von Gioi, "A contrario detection of h.264 video double compression," in 2023 IEEE International Conference on Image Processing (ICIP), 2023.
  • Q. Bammey, R. Grompone von Gioi, and J.-M. Morel, "Automatic detec- tion of demosaicing image artifacts and its use in tampering detection," in 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2018, pp. 424–429.
  • T. Nikoukhah, J. Anger, M. Colom, J.-M. Morel, and R. Grompone von Gioi, "ZERO: a Local JPEG Grid Origin Detector Based on the Number of DCT Zeros and its Applications in Image Forensics," IPOL, 2021.
  • T. Ehret, "Robust copy-move forgery detection by false alarms control," arXiv preprint arXiv:1906.00649, 2019.
  • Q. Bammey, "Analysis and Experimentation on the ManTraNet Image Forgery Detector," Image Processing On Line, vol. 12, pp. 457–468, 2022, https://doi.org/10.5201/ipol.2022.431.
  • H. Mareen, D. V. Bussche, F. Guillaro, D. Cozzolino, G. Van Wallendael, P. Lambert, and L. Verdoliva, "Comprint: Image forgery detection and localization using compression fingerprints," 2022. [Online]. Available: https://arxiv.org/abs/2210.02227
  • D. Cozzolino, G. Poggi, and L. Verdoliva, "Splicebuster: A new blind image splicing detector," in WIFS, 2015.
  • Q. Bammey, T. Nikoukhah, M. Gardella, R. G. von Gioi, M. Colom, and J.-M. Morel, "Non-semantic evaluation of image forensics tools: Methodology and database," in WACV, January 2022, pp. 3751–3760.
  • D.-T. Dang-Nguyen, C. Pasquini, V. Conotter, and G. Boato, "Raise: A raw images dataset for digital image forensics," in Proceedings of the 6th ACM Multimedia Systems Conference, 2015, pp. 219–224.
  • B. K. T. Ho, V. Y. Tseng, M. Ma, and D. T. Chen, "Mathematical model to quantify JPEG block artifacts," in Medical Imaging 1993: Image Capture, Formatting, and Display, Y. Kim, Ed., vol. 1897, International Society for Optics and Photonics. SPIE, 1993, pp. 269 – 275.
  • B. Li, T.-T. Ng, X. Li, S. Tan, and J. Huang, "Revealing the trace of high- quality jpeg compression through quantization noise analysis," IEEE Transactions on Information Forensics and Security, vol. 10, no. 3, pp. 558–573, 2015.
  • B. Li, T.-T. Ng, X. Li, S. Tan, and J. Huang, "Statistical model of jpeg noises and its application in quantization step estimation," IEEE Transactions on Image Processing, vol. 24, no. 5, pp. 1471–1484, 2015.
  • M. Gardella, T. Nikoukhah, Y. Li, and Q. Bammey, "The impact of jpeg compression on prior image noise," in ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, pp. 2689–2693.
  • N. Le and F. Retraint, "An improved algorithm for digital image authentication and forgery localization using demosaicing artifacts," IEEE Access, vol. 7, pp. 125 038–125 053, 2019.
  • Q. Bammey, R. Grompone von Gioi, and J.-M. Morel, "Image Forgeries Detection through Mosaic Analysis: the Intermediate Values Algorithm," Image Processing On Line, vol. 11, pp. 317–343, 2021.
  • S. Mandelli, N. Bonettini, P. Bestagini, and S. Tubaro, "Training cnns in presence of jpeg compression: Multimedia forensics vs computer vision," in 2020 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, 2020, pp. 1–6.