Robust Detection of Image Operator Chain With Two-Stream Convolutional Neural Network

Many forensic techniques have recently been developed to determine whether an image has undergone a specific manipulation operation. When multiple consecutive operations are applied to images, forensic analysts not only need to identify the existence of each manipulation operation, but also to distinguish the order of the involved operations. However, image operator chain detection is still a challenging problem. In this paper, an order forensics framework for detecting image operator chain based on convolutional neural network (CNN) is presented. Two-stream CNN architecture is designed to capture both tampering artifact evidence and local noise residual evidence. Specifically, the new CNN-based method is proposed for forensically detecting a chain made of two image operators, which could automatically learn manipulation detection features directly from image data. Further, we empirically investigate the robustness of our proposed method in two practical scenarios: forensic investigators have no access to the operating parameters, and manipulations are applied to a JPEG compressed image. Experimental results show that the proposed framework not only obtains significant detection performance but also can distinguish the order in some cases that previous works were unable to identify.

[1]  Mauro Barni,et al.  Cnn-Based Detection of Generic Contrast Adjustment with Jpeg Post-Processing , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[2]  Belhassen Bayar,et al.  Constrained Convolutional Neural Networks: A New Approach Towards General Purpose Image Manipulation Detection , 2018, IEEE Transactions on Information Forensics and Security.

[3]  Fernando Pérez-González,et al.  Multiple JPEG compression detection by means of Benford-Fourier coefficients , 2014, 2014 IEEE International Workshop on Information Forensics and Security (WIFS).

[4]  Z. Jane Wang,et al.  Median Filtering Forensics Based on Convolutional Neural Networks , 2015, IEEE Signal Processing Letters.

[5]  Gerald Schaefer,et al.  UCID: an uncompressed color image database , 2003, IS&T/SPIE Electronic Imaging.

[6]  K. J. Ray Liu,et al.  Robust Median Filtering Forensics Using an Autoregressive Model , 2013, IEEE Transactions on Information Forensics and Security.

[7]  Marc Chaumont,et al.  Camera model identification with the use of deep convolutional neural networks , 2016, 2016 IEEE International Workshop on Information Forensics and Security (WIFS).

[8]  Tomás Pevný,et al.  "Break Our Steganographic System": The Ins and Outs of Organizing BOSS , 2011, Information Hiding.

[9]  Xingming Sun,et al.  Segmentation-Based Image Copy-Move Forgery Detection Scheme , 2015, IEEE Transactions on Information Forensics and Security.

[10]  Jessica J. Fridrich,et al.  Scalable Processing History Detector for JPEG Images , 2017, Media Watermarking, Security, and Forensics.

[11]  Belhassen Bayar,et al.  A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer , 2016, IH&MMSec.

[12]  Rainer Böhme,et al.  Revisiting weighted stego-image steganalysis , 2008, Electronic Imaging.

[13]  K. J. Ray Liu,et al.  Forensically determining the order of signal processing operations , 2013, 2013 IEEE International Workshop on Information Forensics and Security (WIFS).

[14]  Kai Wang,et al.  General-purpose image forensics using patch likelihood under image statistical models , 2015, 2015 IEEE International Workshop on Information Forensics and Security (WIFS).

[15]  Jiwu Huang,et al.  Large-Scale JPEG Image Steganalysis Using Hybrid Deep-Learning Framework , 2016, IEEE Transactions on Information Forensics and Security.

[16]  Jiangqun Ni,et al.  A deep learning approach to detection of splicing and copy-move forgeries in images , 2016, 2016 IEEE International Workshop on Information Forensics and Security (WIFS).

[17]  Ingemar J. Cox,et al.  Normalized Energy Density-Based Forensic Detection of Resampled Images , 2012, IEEE Transactions on Multimedia.

[18]  Yao Zhao,et al.  Contrast Enhancement-Based Forensics in Digital Images , 2014, IEEE Transactions on Information Forensics and Security.

[19]  Jiwu Huang,et al.  A universal image forensic strategy based on steganalytic model , 2014, IH&MMSec '14.

[20]  K. J. Ray Liu,et al.  Blind forensics of contrast enhancement in digital images , 2008, 2008 15th IEEE International Conference on Image Processing.

[21]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[22]  Jessica J. Fridrich,et al.  Deep Learning for Detecting Processing History of Images , 2018, Media Watermarking, Security, and Forensics.

[23]  Belhassen Bayar,et al.  Towards Order of Processing Operations Detection in JPEG-compressed Images with Convolutional Neural Networks , 2018, Media Watermarking, Security, and Forensics.

[24]  Alessandro Piva,et al.  Reverse engineering of double compressed images in the presence of contrast enhancement , 2013, 2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP).

[25]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[26]  Alex ChiChung Kot,et al.  Image Recapture Detection with Convolutional and Recurrent Neural Networks , 2017, Media Watermarking, Security, and Forensics.

[27]  Jiwu Huang,et al.  Identification of Various Image Operations Using Residual-Based Features , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  Ming Xu,et al.  Statistical Model-Based Detector via Texture Weight Map: Application in Re-Sampling Authentication , 2019, IEEE Transactions on Multimedia.

[29]  Christian Riess,et al.  Ieee Transactions on Information Forensics and Security an Evaluation of Popular Copy-move Forgery Detection Approaches , 2022 .

[30]  Fernando Pérez-González,et al.  Forensic Detection of Processing Operator Chains: Recovering the History of Filtered JPEG Images , 2015, IEEE Transactions on Information Forensics and Security.

[31]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[32]  Min Wu,et al.  Information Forensics: An Overview of the First Decade , 2013, IEEE Access.

[33]  Jiwu Huang,et al.  Blind Detection of Median Filtering in Digital Images: A Difference Domain Based Approach , 2013, IEEE Transactions on Image Processing.

[34]  Nitin Khanna,et al.  DCT-domain Deep Convolutional Neural Networks for Multiple JPEG Compression Classification , 2017, Signal Process. Image Commun..

[35]  Stefano Tubaro,et al.  Discriminating multiple JPEG compression using first digit features , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[36]  K. J. Ray Liu,et al.  Detectability of the Order of Operations: An Information Theoretic Approach , 2016, IEEE Transactions on Information Forensics and Security.

[37]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[38]  Hany Farid,et al.  Exposing digital forgeries by detecting traces of resampling , 2005, IEEE Transactions on Signal Processing.

[39]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[40]  Belhassen Bayar,et al.  On the robustness of constrained convolutional neural networks to JPEG post-compression for image resampling detection , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[41]  Alessandro Piva,et al.  Reverse engineering of double JPEG compression in the presence of image resizing , 2012, 2012 IEEE International Workshop on Information Forensics and Security (WIFS).

[42]  Pedro Comesaña.  Detection and information theoretic measures for quantifying the distinguishability between multimedia operator chains , 2012, 2012 IEEE International Workshop on Information Forensics and Security (WIFS).