Image tampering detection based on a statistical model

This paper presents a novel method for image manipulation iden- tification of natural images in JPEG format. The image forgery detection technique is based on a signal-dependent noise model that is relevant to de- scribe a natural image acquired by a digital camera. This parametric model is characterized by two fingerprints which are used to falsification identification. The problem is cast in the framework of the hypothesis testing theory. For practical use, the Generalized Likelihood Ratio Tests (GLRT) are presented and their performance is theoretically established. There are different types of image forgery which have been considered in this paper for example re- sampling, Gaussian filtering and median filtering. Experiments with real and simulated images highlight the relevance of the proposed approach.

[1]  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).

[2]  Florent Retraint,et al.  Camera model identification based on the generalized noise model in natural images , 2016, Digit. Signal Process..

[3]  E. Lehmann.  Testing Statistical Hypotheses , 1960 .

[4]  Florent Retraint,et al.  Generalized signal-dependent noise model and parameter estimation for natural images , 2015, Signal Process..

[5]  Florent Retraint,et al.  Camera Model Identification Based on the Heteroscedastic Noise Model , 2014, IEEE Transactions on Image Processing.

[6]  Xiao Jin,et al.  Hierarchical image resampling detection based on blind deconvolution , 2017, J. Vis. Commun. Image Represent..

[7]  T. H. Thai,et al.  Statistical model of natural images , 2012, 2012 19th IEEE International Conference on Image Processing.

[8]  Xianfeng Zhao,et al.  Adversarial Learning for Constrained Image Splicing Detection and Localization Based on Atrous Convolution , 2019, IEEE Transactions on Information Forensics and Security.

[9]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[10]  Hoai Phuong Nguyen,et al.  An Image Forgery Detection Solution based on DCT Coefficient Analysis , 2019, ICISSP.

[11]  Kang Hyeon Rhee.  Median filtering detection based on variations and residuals in image forensics , 2017 .

[12]  Kang Hyeon Rhee,et al.  Gaussian filtering detection using band pass residual and contrast of forgery image , 2016, 2016 IEEE 7th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON).

[13]  K. Rhee.  Forensic Detection Using Bit-Planes Slicing of Median Filtering Image , 2019, IEEE Access.

[14]  Florent Retraint,et al.  Identifying Individual Camera Device From RAW Images , 2018, IEEE Access.

[15]  Hugues Talbot,et al.  Automatic Image Splicing Detection Based on Noise Density Analysis in Raw Images , 2016, ACIVS.

[16]  Judith Redi,et al.  Digital image forensics: a booklet for beginners , 2010, Multimedia Tools and Applications.

[17]  Florent Retraint,et al.  Statistical Detector of Resampled TIFF Images , 2018, 2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[18]  Hui Zeng,et al.  Deep Residual Learning Using Data Augmentation for Median Filtering Forensics of Digital Images , 2019, IEEE Access.

[19]  Rainer Böhme,et al.  The Dresden Image Database for Benchmarking Digital Image Forensics , 2010, J. Digit. Forensic Pract..

[20]  Florent Retraint,et al.  Blind forensics tool of falsification for RAW images , 2017, 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[21]  P. Rousseeuw,et al.  Alternatives to the Median Absolute Deviation , 1993 .

[22]  Florent Retraint,et al.  Exposing image resampling forgery by using linear parametric model , 2016, Multimedia Tools and Applications.

[23]  Xiao Jin,et al.  AMFNet: An Adversarial Network for Median Filtering Detection , 2018, IEEE Access.

[24]  Florent Retraint,et al.  An Improved Algorithm for Digital Image Authentication and Forgery Localization Using Demosaicing Artifacts , 2019, IEEE Access.

[25]  Kang Hyeon Rhee,et al.  Gaussian filtering detection based on features of residuals in image forensics , 2016, 2016 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future (RIVF).

[26]  Xuanjing Shen,et al.  Image splicing detection based on Markov features in discrete octonion cosine transform domain , 2018, IET Image Process..

[27]  Florent Retraint,et al.  Individual camera device identification from JPEG images , 2017, Signal Process. Image Commun..

[28]  Chia-Chen Lin,et al.  Blind Dual Watermarking for Color Images’ Authentication and Copyright Protection , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[29]  Clayton Scott,et al.  Performance Measures for Neyman–Pearson Classification , 2007, IEEE Transactions on Information Theory.

[30]  Hua Han,et al.  Robust Median Filtering Forensics by CNN-Based Multiple Residuals Learning , 2019, IEEE Access.

[31]  Yao Zhao,et al.  Robust median filtering detection based on local difference descriptor , 2017, Signal Process. Image Commun..