Camera-based Image Forgery Localization using Convolutional Neural Networks

Camera fingerprints are precious tools for a number of image forensics tasks. A well-known example is the photo response non-uniformity (PRNU) noise pattern, a powerful device fingerprint. Here, to address the image forgery localization problem, we rely on noiseprint, a recently proposed CNN-based camera model fingerprint. The CNN is trained to minimize the distance between same-model patches, and maximize the distance otherwise. As a result, the noiseprint accounts for model-related artifacts just like the PRNU accounts for device-related nonuniformities. However, unlike the PRNU, it is only mildly affected by residuals of high-level scene content. The experiments show that the proposed noiseprint-based forgery localization method improves over the PRNU-based reference.

[1]  Fouad Khelifi,et al.  On the SPN Estimation in Image Forensics: A Systematic Empirical Evaluation , 2017, IEEE Transactions on Information Forensics and Security.

[2]  Mo Chen,et al.  Determining Image Origin and Integrity Using Sensor Noise , 2008, IEEE Transactions on Information Forensics and Security.

[3]  Jean-Luc Dugelay,et al.  Videos versus still images: Asymmetric sensor pattern noise comparison on mobile phones , 2017, Media Watermarking, Security, and Forensics.

[4]  Rainer Böhme,et al.  The 'Dresden Image Database' for benchmarking digital image forensics , 2010, SAC '10.

[5]  Davide Cozzolino,et al.  A feature-based approach for image tampering detection and localization , 2014, 2014 IEEE International Workshop on Information Forensics and Security (WIFS).

[6]  James Hays,et al.  Localizing and Orienting Street Views Using Overhead Imagery , 2016, ECCV.

[7]  Jiwu Huang,et al.  Evaluation of random field models in multi-modal unsupervised tampering localization , 2016, 2016 IEEE International Workshop on Information Forensics and Security (WIFS).

[8]  Lei Zhang,et al.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising , 2016, IEEE Transactions on Image Processing.

[9]  Marco Fontani,et al.  VISION: a video and image dataset for source identification , 2017, EURASIP Journal on Information Security.

[10]  Chang-Tsun Li,et al.  Source Camera Identification Using Enhanced Sensor Pattern Noise , 2009, IEEE Transactions on Information Forensics and Security.

[11]  Pawel Korus,et al.  Digital image integrity - a survey of protection and verification techniques , 2017, Digit. Signal Process..

[12]  Davide Cozzolino,et al.  Noiseprint: A CNN-Based Camera Model Fingerprint , 2018, IEEE Transactions on Information Forensics and Security.

[13]  Luisa Verdoliva,et al.  A Bayesian-MRF Approach for PRNU-Based Image Forgery Detection , 2014, IEEE Transactions on Information Forensics and Security.

[14]  Paolo Bestagini,et al.  Tampering Detection and Localization Through Clustering of Camera-Based CNN Features , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[15]  Chang-Tsun Li,et al.  Color-Decoupled Photo Response Non-Uniformity for Digital Image Forensics , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[16]  Luisa Verdoliva,et al.  On the influence of denoising in PRNU based forgery detection , 2010, MiFor '10.

[17]  Jiwu Huang,et al.  Multi-Scale Analysis Strategies in PRNU-Based Tampering Localization , 2017, IEEE Transactions on Information Forensics and Security.

[18]  Jan Lukás,et al.  Detecting digital image forgeries using sensor pattern noise , 2006, Electronic Imaging.

[19]  Silvio Savarese,et al.  Deep Metric Learning via Lifted Structured Feature Embedding , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Jessica Fridrich,et al.  Sensor Defects in Digital Image Forensic , 2013 .