Divya Singhal
Abhinav Gupta
Skip Abstract Section
Abstract
Increasingly sophisticated image editing tools make it easy to modify images. Often these modifications are elaborate, convincing, and undetectable by even careful human inspection. These considerations have prompted the development of forensic algorithms and approaches to detect modifications done to an image. However, these detectors are model-driven (i.e., manipulation-specific) and the choice of a potent detector requires knowledge of the type of manipulation, something that cannot be known (a priori). Thus, the latest effort is directed towards developing model-free (i.e., generalized) detectors capable of detecting multiple manipulation types. In this article, we propose a novel detector capable of exposing seven different manipulation types in low-resolution compressed images. Our proposed approach is based on a two-layer convolutional neural network (CNN) to extract frequency domain features of image median filtered residual that are classified using two different classifiers—softmax and extremely randomized trees. Extensive experiments demonstrate the efficacy of proposed detector over existing state-of-the-art detectors.
- Darius Afchar, Vincent Nozick, Junichi Yamagishi, and Isao Echizen. 2018. MesoNet: A compact facial video forgery detection network. CoRR abs/1809.00888 (2018).Google Scholar
- M. Barni, A. Costanzo, E. Nowroozi, and B. Tondi. 2018. CNN based detection of generic contrast adjustment with jpeg post-processing. In Proceedings of the IEEE International Conference on Image Processing (ICIP’18). 3803--3807.Google Scholar
- Patrick Bas, Tomáš Filler, and Tomáš Pevný. 2011. Break Our Steganographic System: The Ins and Outs of Organizing BOSS. Springer, Berlin, 59--70. DOI:https://doi.org/10.1007/978-3-642-24178-9_5Google Scholar
- Patrick Bas and Teddy Furon. 2007. BOWS-2. Retrieved on May 2020 from http://bows2.ec-lille.fr/.Google Scholar
- Belhassen Bayar and Matthew C. Stamm. 2018. Constrained convolutional neural networks: A new approach towards general purpose image manipulation detection. IEEE Trans. Inf. Forens. Sec. 13 (2018), 2691--2706. Issue 11.Google ScholarCross Ref
- Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, Berlin.Google ScholarDigital Library
- Gang Cao, Yao Zhao, Rongrong Ni, and Xuelong Li. 2014. Contrast enhancement-based forensics in digital images. IEEE Trans. Inf. Forens. Sec. 9, 3 (Mar. 2014), 515--525. DOI:https://doi.org/10.1109/TIFS.2014.2300937Google ScholarDigital Library
- Bolin Chen, Haodong Li, and Weiqi Luo. 2017. Image processing operations identification via convolutional neural network. CoRR abs/1709.02908 (2017).Google Scholar
- Chenglong Chen, Jiangqun Ni, and Jiwu Huang. 2013. Blind detection of median filtering in digital images: A difference domain based approach. IEEE Trans. Image Proc. 22, 12 (Dec. 2013), 4699--4710. DOI:https://doi.org/10.1109/TIP.2013.2277814Google Scholar
- Jiansheng Chen, Xiangui Kang, Ye Liu, and Z. J. Wang. 2015. Median filtering forensics based on convolutional neural networks. IEEE Sig. Proc. Lett. 22 (2015), 1849--1853.Google ScholarCross Ref
- Djork-Arné Clevert, Thomas Unterthiner, and Sepp Hochreiter. 2015. Fast and accurate deep network learning by exponential linear units (ELUs). CoRR abs/1511.07289 (2015).Google Scholar
- Davide Cozzolino, Giovanni Poggi, and Luisa Verdoliva. 2017. Recasting residual-based local descriptors as convolutional neural networks: An application to image forgery detection. In Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia Security (IH-MMSec’17). ACM, New York, NY, 159--164. DOI:https://doi.org/10.1145/3082031.3083247Google ScholarDigital Library
- Yann Le Cun. 1988. A theoretical framework for back-propagation. In Proceedings of the 1988 Connectionist Models Summer School, D. Touretzky, G. Hinton, and T. Sejnowski (Eds.). CMU, Pittsburg, PA, 21--28.Google Scholar
- Image Database. 2013. IEEE IFS-TC Image Forensics Challenge. Retrieved from http://ifc.recod.ic.unicamp.br/fc.website/index.py?sec=5.Google Scholar
- Burhan Ergen. 2016. Scale invariant and fixed-length feature extraction by integrating discrete cosine transform and autoregressive signal modeling for palmprint identification. Turk. J. Elect. Eng. Comput. Sci. 24 (Jan. 2016), 1768--1781. DOI:https://doi.org/10.3906/elk-1309-65Google Scholar
- W. Fan, K. Wang, and F. Cayre. 2015. General-purpose image forensics using patch likelihood under image statistical models. In Proceedings of the IEEE International Workshop on Information Forensics and Security (WIFS’15). 1--6. DOI:https://doi.org/10.1109/WIFS.2015.7368606Google Scholar
- Xiaoying Feng, Ingemar J. Cox, and Gwenaël J. Doërr. 2012. Normalized energy density-based forensic detection of resampled images. IEEE Trans. Multimedia 14, 3--1 (2012), 536--545. DOI:https://doi.org/10.1109/TMM.2012.2191946Google Scholar
- J. Fridrich and J. Kodovsky. 2012. Rich models for steganalysis of digital images. IEEE Trans. Inf. Forens. Sec. 7, 3 (June 2012), 868--882. DOI:https://doi.org/10.1109/TIFS.2012.2190402Google ScholarDigital Library
- Thomas Gloe and Rainer Böhme. 2010. The “Dresden Image Database” for benchmarking digital image forensics. In Proceedings of the ACM Symposium on Applied Computing (SAC’10). ACM, New York, NY, 1584--1590. DOI:https://doi.org/10.1145/1774088.1774427Google ScholarDigital Library
- Abhinav Gupta and Divya Singhal. 2018. Analytical global median filtering forensics based on moment histograms. ACM Trans. Multimedia Comput. Commun. Applic. 14, 2 (Apr. 2018), 44:1--44:23. DOI:https://doi.org/10.1145/3176650Google ScholarDigital Library
- K. He and J. Sun. 2015. Convolutional neural networks at constrained time cost. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15). 5353--5360. DOI:https://doi.org/10.1109/CVPR.2015.7299173Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2015. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In Proceedings of the IEEE International Conference on Computer Vision (ICCV’15). IEEE Computer Society, Washington, DC, 1026--1034. DOI:https://doi.org/10.1109/ICCV.2015.123Google ScholarDigital Library
- Lars Hertel, Huy Phan, and Alfred Mertins. 2016. Comparing time and frequency domain for audio event recognition using deep learning. CoRR abs/1603.05824 (2016).Google Scholar
- Geoffrey E. Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2012. Improving neural networks by preventing co-adaptation of feature detectors. CoRR abs/1207.0580 (2012).Google Scholar
- Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. 448--456. Retrieved from http://jmlr.org/proceedings/papers/v37/ioffe15.pdf.Google Scholar
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM International Conference on Multimedia (MM’14). ACM, New York, NY, 675--678. DOI:https://doi.org/10.1145/2647868.2654889Google ScholarDigital Library
- L. Kang, J. Kumar, P. Ye, Y. Li, and D. Doermann. 2014. Convolutional neural networks for document image classification. In Proceedings of the 22nd International Conference on Pattern Recognition. 3168--3172. DOI:https://doi.org/10.1109/ICPR.2014.546Google Scholar
- Xiangui Kang, Matthew C. Stamm, Anjie Peng, and K. J. Ray Liu. 2013. Robust median filtering forensics using an autoregressive model. IEEE Trans. Inf. Forens. Sec. 8, 9 (Sept. 2013), 1456--1468. DOI:https://doi.org/10.1109/TIFS.2013.2273394Google ScholarDigital Library
- Matthias Kirchner and Jessica Fridrich. 2010. On detection of median filtering in digital images. In Proc. SPIE Media Forens. Sec. II, Vol. 7541. SPIE, 754110--754110--12. DOI:https://doi.org/10.1117/12.839100Google Scholar
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 1097--1105. Retrieved from DOI:http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdfGoogle ScholarDigital Library
- Yann LeCun and Yoshua Bengio. 1998. Convolutional networks for images, speech, and time series. In The Handbook of Brain Theory and Neural Networks. The MIT Press, Cambridge, MA, 255--258. Retrieved from http://dl.acm.org/citation.cfm?id=303568.303704.Google Scholar
- Yann LeCun, Léon Bottou, Genevieve B. Orr, and Klaus-Robert Müller. 1998. Efficient BackProp. In Neural Networks: Tricks of the Trade, This Book Is an Outgrowth of a 1996 NIPS Workshop. Springer-Verlag, London, UK, 9--50. Retrieved from http://dl.acm.org/citation.cfm?id=645754.668382.Google ScholarDigital Library
- S. Lee, T. Chen, L. Yu, and C. Lai. 2018. Image classification based on the boost convolutional neural network. IEEE Access 6 (2018), 12755--12768. DOI:https://doi.org/10.1109/ACCESS.2018.2796722Google ScholarCross Ref
- Haodong Li, Weiqi Luo, Xiaoqing Qiu, and Jiwu Huang. 2018. Identification of various image operations using residual-based features. IEEE Trans. Circ. Syst. Video Technol. 28, 1 (2018), 31--45. DOI:https://doi.org/10.1109/TCSVT.2016.2599849Google ScholarDigital Library
- Andrew L. Maas, Awni Y. Hannun, and Andrew Y. Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In Proceedings of the ICML Workshop on Deep Learning for Audio, Speech, and Language Processing.Google Scholar
- Aravindh Mahendran and Andrea Vedaldi. 2016. Visualizing deep convolutional neural networks using natural pre-images. Int. J. Comput. Vision 120, 3 (Dec. 2016), 233--255. DOI:https://doi.org/10.1007/s11263-016-0911-8Google ScholarCross Ref
- USDA NRCS. 2014. Natural Resources Conservation Service Photo Gallery, United States Department of Agriculture. Retrieved from http://plants.usda.gov/.Google Scholar
- C. Pasquini, P. Schöttle, R. Böhme, G. Boato, and F. Pèrez-Gonzàlez. June 2016. Forensics of high quality and nearly identical jpeg image re-compression. InProceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security (IHMMSec’16). 11--21.Google Scholar
- Tomàš Pevnỳ, Patrick Bas, and Jessica Fridrich. 2010. Steganalysis by subtractive pixel adjacency matrix. IEEE Trans. Inf. Forens. Sec. 5, 2 (June 2010), 215--224. DOI:https://doi.org/10.1109/TIFS.2010.2045842Google ScholarDigital Library
- Alin C. Popescu and Hany Farid. 2005. Exposing digital forgeries by detecting traces of resampling. IEEE Trans. Sig. Proc. 53, 2 (Feb. 2005), 758--767. DOI:https://doi.org/10.1109/TSP.2004.839932Google ScholarCross Ref
- Xiaoqing Qiu, Haodong Li, Weiqi Luo, and Jiwu Huang. 2014. A universal image forensic strategy based on steganalytic model. In Proceedings of the 2nd ACM Workshop on Information Hiding and Multimedia Security (IH-MMSec’14). ACM, New York, NY, 165--170. DOI:https://doi.org/10.1145/2600918.2600941Google ScholarDigital Library
- Herbert Robbins and Sutton Monro. 1951. A stochastic approximation method. Ann. Math. Statist. 22, 3 (9 1951), 400--407. DOI:https://doi.org/10.1214/aoms/1177729586Google Scholar
- Joshua Rothman. 2018. In the age of A.I., is seeing still believing? The New Yorker (12 Nov. 2018). Retrieved from https://www.newyorker.com/magazine/2018/11/12/in-the-age-of-ai-is-seeing-still-believing.Google Scholar
- Gerald Schaefer and Michal Stich. 2003. UCID: An uncompressed color image database. In Proc. SPIE, Vol. 5307. SPIE, 472--480. DOI:https://doi.org/10.1117/12.525375Google Scholar
- Dominik Scherer, Andreas Müller, and Sven Behnke. 2010. Evaluation of pooling operations in convolutional architectures for object recognition. In Proceedings of the 20th International Conference on Artificial Neural Networks: Part III (ICANN’10). Springer-Verlag, 92--101. Retrieved from DOI:http://dl.acm.org/citation.cfm?id=1886436.1886447Google ScholarDigital Library
- Yun Q. Shi, Patchara Sutthiwan, and Licong Chen. 2013. Textural features for steganalysis. In Proceedings of the 14th International Conference on Information Hiding (IH’12). Springer-Verlag, 63--77. DOI:https://doi.org/10.1007/978-3-642-36373-3_5Google ScholarDigital Library
- Matthew C. Stamm and K. J. Ray Liu. 2010. Forensic detection of image manipulation using statistical intrinsic fingerprints. IEEE Trans. Inf. Forens. Sec. 5, 3 (Sept. 2010), 492--506. DOI:https://doi.org/10.1109/TIFS.2010.2053202Google ScholarDigital Library
- M. C. Stamm, M. Wu, and K. J. R. Liu. 2013. Information forensics: An overview of the first decade. IEEE Access 1 (2013), 167--200. DOI:https://doi.org/10.1109/ACCESS.2013.2260814Google ScholarCross Ref
- C. Szegedy, Wei Liu, Yangqing Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15), Vol. 00. 1--9. DOI:https://doi.org/10.1109/CVPR.2015.7298594Google Scholar
- Hongshen Tang, Rongrong Ni, Yao Zhao, and Xiaolong Li. 2017. Detection of various image operations based on CNN. In Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC’17). 1479--1485. DOI:https://doi.org/10.1109/APSIPA.2017.8282267Google ScholarCross Ref
- Hongshen Tang, Rongrong Ni, Yao Zhao, and Xiaolong Li. 2018. Median filtering detection of small-size image based on CNN. J. Vis. Commun. Image Repres. 51 (2018), 162--168. DOI:https://doi.org/10.1016/j.jvcir.2018.01.011Google ScholarCross Ref
- Thanh Hai Thai, Rèmi Cogranne, Florent Retraint, and Thi-Ngoc-Canh Doan. 2017. JPEG quantization step estimation and its applications to digital image forensics. IEEE Trans. Inf. Forens. Sec. 12, 1 (Jan. 2017), 123--133. DOI:https://doi.org/10.1109/TIFS.2016.2604208Google ScholarDigital Library
- A. Toshev and C. Szegedy. 2014. DeepPose: Human pose estimation via deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1653--1660. DOI:https://doi.org/10.1109/CVPR.2014.214Google Scholar
- H. K. Vydana and A. K. Vuppala. 2017. Investigative study of various activation functions for speech recognition. In Proceedings of the 23rd National Conference on Communications (NCC’17). 1--5. DOI:https://doi.org/10.1109/NCC.2017.8077043Google Scholar
- Dong-ping Wang, Tiegang Gao, and Fusheng Yang. 2018. A forensic algorithm against median filtering based on coefficients of image blocks in frequency domain. Multimedia Tools Applic. 77 (29 Jan. 2018). DOI:https://doi.org/10.1007/s11042-018-5651-zGoogle Scholar
- Qing Wang and Rong Zhang. 2016. Double JPEG compression forensics based on a convolutional neural network. EURASIP J. Inf. Sec. 2016, 1 (10. Oct 2016), 23. DOI:https://doi.org/10.1186/s13635-016-0047-yGoogle Scholar
- Pengpeng Yang, Rongrong Ni, Yao Zhao, Gang Cao, Haorui Wu, and Wei Zhao. 2018. Robust contrast enhancement forensics using convolutional neural networks. CoRR abs/1803.04749 (2018).Google Scholar
- S. Yu, Y. Cheng, L. Xie, and S. Li. 2017. Fully convolutional networks for action recognition. IET Comput. Vis. 11, 8 (2017), 744--749. DOI:https://doi.org/10.1049/iet-cvi.2017.0005Google ScholarCross Ref
- Hai Dong Yuan. 2011. Blind forensics of median filtering in digital images. IEEE Trans. Inf. Forens. Sec. 6, 4 (Dec. 2011), 1335--1345. DOI:https://doi.org/10.1109/TIFS.2011.2161761Google ScholarDigital Library
- Peng Zhou, Xintong Han, Vlad I. Morariu, and Larry S. Davis. 2018. Learning rich features for image manipulation detection. CoRR abs/1805.04953 (2018).Google Scholar
Index Terms
- CNN-based Multiple Manipulation Detector Using Frequency Domain Features of Image Residuals
Recommendations
A Transformer based Approach for Image Manipulation Chain Detection
MM '21: Proceedings of the 29th ACM International Conference on MultimediaImage manipulation chain detection aims to identify the existence of involved operations and also their orders, playing an important role in multimedia forensics and image analysis. However,all the existing algorithms model the manipulation chain ...
A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer
IH&MMSec '16: Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia SecurityWhen creating a forgery, a forger can modify an image using many different image editing operations. Since a forensic examiner must test for each of these, significant interest has arisen in the development of universal forensic algorithms capable of ...
Fake Faces Identification via Convolutional Neural Network
IH&MMSec '18: Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia SecurityGenerative Adversarial Network (GAN) is a prominent generative model that are widely used in various applications. Recent studies have indicated that it is possible to obtain fake face images with a high visual quality based on this novel model. If ...
Comments