Abstract
Digital image information can be easily tampered with to harm the integrity of someone. Thus, recognizing the truthfulness and processing history of an image is one of the essential concerns in multimedia forensics. Numerous forensic methods have been developed by researchers with the ability to detect targeted editing operations. However, creating a unified forensic approach capable of detecting multiple image manipulations remains a challenging problem. In this article, a new general-purpose forensic approach is designed based on a shallow densely connected convolutional neural network (SDCN2) that exploits local dense connections and global residual learning. The residual domain is considered in the proposed network rather than the spatial domain to analyze the image manipulation artifacts because the residual domain is less dependent on image content information. To attain this purpose, a residual convolutional layer is employed at the beginning of the proposed model to adaptively learn the image manipulation features by suppressing the image content information. Then, the obtained image residuals or prediction error features are further processed by the shallow densely connected convolutional neural network for high-level feature extraction. In addition, the hierarchical features produced by the densely connected blocks and prediction error features are fused globally for better information flow across the network. The extensive experiment results show that the proposed scheme outperforms the existing state-of-the-art general-purpose forensic schemes even under anti-forensic attacks, when tested on large-scale datasets. The proposed model offers overall detection accuracies of 98.34% and 99.22% for BOSSBase and Dresden datasets, respectively, for multiple image manipulation detection. Moreover, the proposed network is highly efficient in terms of computational complexity as compared to the existing approaches.
- [1] . 2016. Multimedia forensics: Discovering the history of multimedia contents. In Proceedings of the 17th International Conference on Computer Systems and Technologies (CompSysTech’16). 5–16.Google Scholar
Digital Library
- [2] . 2019. Teaching digital signal processing with a challenge on image forensics. IEEE Signal Processing Magazine 36, 2 (2019), 101–109.Google Scholar
Cross Ref
- [3] . 2013. Information forensics: An overview of the first decade. IEEE Access 1 (2013), 167–200.Google Scholar
Cross Ref
- [4] . 2005. Exposing digital forgeries by detecting traces of resampling. IEEE Transactions on Signal Processing 53, 2 (2005), 758–767.Google Scholar
Digital Library
- [5] . 2008. Fast and reliable resampling detection by spectral analysis of fixed linear predictor residue. In Proceedings of the 10th ACM Workshop on Multimedia and Security (MM&Sec’08). 11–20.Google Scholar
Digital Library
- [6] . 2010. On the role of differentiation for resampling detection. In Proceedings of the 2010 IEEE International Conference on Image Processing. 1753–1756.Google Scholar
Cross Ref
- [7] . 2012. Normalized energy density-based forensic detection of resampled images. IEEE Transactions on Multimedia 14, 3 (2012), 536–545.Google Scholar
Digital Library
- [8] . 2008. Blind authentication using periodic properties of interpolation. IEEE Transactions on Information Forensics and Security 3, 3 (2008), 529–538.Google Scholar
Digital Library
- [9] . 2011. Detection of non-aligned double JPEG compression with estimation of primary compression parameters. In Proceedings of the 2011 18th IEEE International Conference on Image Processing. 1929–1932.Google Scholar
Cross Ref
- [10] . 2012. Image forgery localization via block-grained analysis of JPEG artifacts. IEEE Transactions on Information Forensics and Security 7, 3 (2012), 1003–1017.Google Scholar
Digital Library
- [11] . 2006. JPEG compression history estimation for color images. IEEE Transactions on Image Processing 15, 6 (2006), 1365–1378.Google Scholar
Digital Library
- [12] . 2008. A convolutive mixing model for shifted double JPEG compression with application to passive image authentication. In Proceedings of the 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing. 1661–1664.Google Scholar
Cross Ref
- [13] . 2010. On detection of median filtering in digital images. Proceedings of SPIE: Media Forensics and Security II 7541 (2010), 1–6.Google Scholar
- [14] . 2013. Robust median filtering forensics using an autoregressive model. IEEE Transactions on Information Forensics and Security 8, 9 (2013), 1456–1468.Google Scholar
Digital Library
- [15] . 2010. Forensic detection of median filtering in digital images. In Proceedings of the 2010 IEEE International Conference on Multimedia and Expo (ICME’10). 89–94.Google Scholar
Cross Ref
- [16] . 2011. Median filtering detection using edge based prediction matrix. In Digital Forensics and Watermarking. Lecture Notes in Computer Science, 7128. Springer, 361–375.Google Scholar
- [17] . 2010. Forensic detection of image manipulation using statistical intrinsic fingerprints. IEEE Transactions on Information Forensics and Security 5, 3 (2010), 492–506.Google Scholar
Digital Library
- [18] . 2009. Detect piecewise linear contrast enhancement and estimate parameters using spectral analysis of image histogram. In Proceedings of the IET International Communication Conference on Wireless Mobile and Computing (CCWMC’09). 94–97.Google Scholar
- [19] . 2008. Blind forensics of contrast enhancement in digital images. In Proceedings of the 2008 15th IEEE International Conference on Image Processing. 3112–3115.Google Scholar
Cross Ref
- [20] . 2010. Forensic estimation and reconstruction of a contrast enhancement mapping. In Proceedings of the 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing. 1698–1701.Google Scholar
Cross Ref
- [21] . 2013. A variational approach to JPEG anti-forensics. In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing. 3058–3062.Google Scholar
Cross Ref
- [22] . 2014. JPEG anti-forensics with improved tradeoff between forensic undetectability and image quality. IEEE Transactions on Information Forensics and Security 9, 8 (2014), 1211–1226.Google Scholar
Digital Library
- [23] . 2015. Median filtered image quality enhancement and anti-forensics via variational deconvolution. IEEE Transactions on Information Forensics and Security 10, 5 (2015), 1076–1091.Google Scholar
Digital Library
- [24] . 2016. ACE—An effective anti-forensic contrast enhancement technique. IEEE Signal Processing Letters 23, 2 (2016), 212–216.Google Scholar
Cross Ref
- [25] . 2012. Rich models for steganalysis of digital images. IEEE Transactions on Information Forensics and Security 7, 3 (2012), 868–882.Google Scholar
Digital Library
- [26] . 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). 165–170.Google Scholar
Digital Library
- [27] . 2010. Steganalysis by subtractive pixel adjacency matrix. IEEE Transactions on Information Forensics and Security 5, 2 (2010), 215–224.Google Scholar
Digital Library
- [28] . 2015. General-purpose image forensics using patch likelihood under image statistical models. In Proceedings of the 2015 IEEE International Workshop on Information Forensics and Security (WIFS’15). 1–6.Google Scholar
Cross Ref
- [29] . 2016. A multi-purpose countermeasure against image anti-forensics using autoregressive model. Neurocomputing 189 (2016), 117–122.Google Scholar
Digital Library
- [30] . 2018. Identification of various image operations using residual-based features. IEEE Transactions on Circuits and Systems for Video Technology 28, 1 (2018), 31–45.Google Scholar
Digital Library
- [31] . 2019. Counter JPEG anti-forensic approach based on the second-order statistical analysis. IEEE Transactions on Information Forensics and Security 14, 5 (2019), 1194–1209.Google Scholar
Digital Library
- [32] . 2016. A deep learning approach to universal image manipulation detection using a new convolutional layer. In Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec’16). 5–10.Google Scholar
Digital Library
- [33] . 2017. A multi-purpose image counter-anti-forensic method using convolutional neural networks. In Proceedings of the International Workshop on Digital Forensics and Watermarking (IWDW’17). 3–15.Google Scholar
Cross Ref
- [34] . 2018. Universal image manipulation detection using deep Siamese convolutional neural network.
arXiv:1808.06323v2 [cs.CV] (2018).Google Scholar - [35] . 2018. Constrained convolutional neural networks: A new approach towards general purpose image manipulation detection. IEEE Transactions on Information Forensics and Security 13, 11 (2018), 2691–2706.Google Scholar
Cross Ref
- [36] . 2020. Xception-based general forensic method on small-size images. In Advances in Intelligent Information Hiding and Multimedia Signal Processing. Springer, 361–369.Google Scholar
- [37] . 2020. CNN-based multiple manipulation detector using frequency domain features of image residuals. ACM Transactions on Intelligent Systems and Technology 11, 4 (2020), Article
40 , 26 pages.Google ScholarDigital Library
- [38] . 2020. Robust detection of image operator chain with two-stream convolutional neural network. IEEE Journal of Selected Topics in Signal Processing 14, 5 (2020), 955–968.Google Scholar
Cross Ref
- [39] . 2009. On resampling detection in re-compressed images. In Proceedings of the 2009 1st IEEE International Workshop on Information Forensics and Security (WIFS’09). 21–25.Google Scholar
Cross Ref
- [40] . 2015. Median filtering forensics based on convolutional neural networks. IEEE Signal Processing Letters 22, 11 (2015), 1849–1853.Google Scholar
Cross Ref
- [41] . 2020. Constrained R-CNN: A general image manipulation detection model. In Proceedings of the IEEE International Conference on Multimedia and Expo (ICME’20). 1–6.Google Scholar
Cross Ref
- [42] . 2014. ADAM: A method for stochastic optimization.
arXiv:1412.6980v9 [cs.LG] (2014).Google Scholar - [43] . 2017. Design principles of convolutional neural networks for multimedia forensics. In Proceedings of the 2017 IS&T International Symposium on Electronic Imaging: Media Watermarking, Security, and Forensics. 77–86.Google Scholar
Cross Ref
- [44] . 2017. Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). 4700–4708.Google Scholar
Cross Ref
- [45] . 2018. Densely connected convolutional neural network for multi-purpose image forensics under antiforensic attacks. In Proceedings of the 6th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec’18). 91–96.Google Scholar
Digital Library
- [46] . 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 770–778.Google Scholar
Cross Ref
- [47] . 2016. Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters 23, 5 (2016), 708–712.Google Scholar
Cross Ref
- [48] . 2011. “Break our steganographic system”: The ins and outs of organizing BOSS. In Information Hiding. Lecture Notes in Computer Science, 6958. Springer, 59–70.Google Scholar
Cross Ref
- [49] . 2010. The ‘Dresden Image Database’ for benchmarking digital image forensics. In Proceedings of the 2010 ACM Symposium on Applied Computing (SAC’10). 1584–1590.Google Scholar
Digital Library
- [50] . 2017. The marginal value of adaptive gradient methods in machine learning. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). 4151–4161.Google Scholar
Digital Library
- [51] . 2011. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 3 (2011), 1–27.Google Scholar
Digital Library
- [52] . 2017. Grad-CAM: Visual explanations from deep networks via gradient-based localization. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV’17). 618–626.Google Scholar
Cross Ref
- [53] . 2018. Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks. In Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision (WACV’18). 839–847.Google Scholar
Cross Ref
Index Terms
SDCN2: A Shallow Densely Connected CNN for Multi-Purpose Image Manipulation Detection
Recommendations
A multi-purpose image forensic method using densely connected convolutional neural networks
Multi-purpose forensics is attracting increasing attention worldwide. In this paper, we propose a multi-purpose method based on densely connected convolutional neural networks (CNNs) for simultaneous detection of 11 different types of image ...
Densely connected AutoEncoders for image compression
ICIGP '19: Proceedings of the 2nd International Conference on Image and Graphics ProcessingImage compression, which is a type of data compression applied to digital images, has been a fundamental research topic for many decades. Recent image techniques produce very large amounts of data, which may make it prohibitive to storage and ...
Efficient densely connected convolutional neural networks
Highlights- Proposed two efficient densely connected ConvNets, DesneDsc and Dense2Net.
- ...
Graphical abstractDisplay Omitted
AbstractRecent works have shown that convolutional neural networks (CNNs) are parameter redundant, which limits the application of CNNs in Mobile devices with limited memory and computational resources. In this paper, two novel and efficient ...






Comments