Noiseprint: A CNN-Based Camera Model Fingerprint

By Davide Cozzolino, Luisa Verdoliva. IEEE Transactions on Information Forensics and Security, 2018

492 citations recorded by the source corpus.

Forensic analyses of digital images rely heavily on the traces of in-camera and out-camera processes left on the acquired images. Such traces represent a sort of camera fingerprint. If one is able to recover them, by suppressing the high-level scene content and other disturbances, a number of forensic tasks can be easily accomplished. A notable example is the PRNU pattern, which can be regarded as a device fingerprint, and has received great attention in multimedia forensics. In this paper, we propose a method to extract a camera model fingerprint, called noiseprint, where the scene content is largely suppressed and model-related artifacts are enhanced. This is obtained by means of a Siamese network, which is trained with pairs of image patches coming from the same (label +1) or different (label −1) cameras. Although the noiseprints can be used for a large variety of forensic tasks, in this paper we focus on image forgery localization. Experiments on several datasets widespread in the forensic community show noiseprint-based methods to provide state-of-the-art performance.

Subfields: Computer Vision and Pattern Recognition, Law

View Paper: https://www.semanticscholar.org/paper/694cccc7205053af917d1d038d8fc4ba45777959

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Law

Citations in the corpus

Uformer: A General U-Shaped Transformer for Image Restoration (2021, background): “The techniques may destroy the original patterns for camera identification and multi-media copyright [11], which hurts the authenticity for image forensics.”
Exposing DeepFake Videos By Detecting Face Warping Artifacts (2018, methodology): “NoisePrint [6] employed CNN model to trace device fingerprints for forgery detection.”
Do GANs Leave Artificial Fingerprints? (2018, background): “), leaves further model-related marks on the images, which can be used to extract a model fingerprint [12].”
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization (2021, background): “, splicing [2, 5, 10, 11, 23, 29, 41, 62], copy-move [9, 24, 59, 63, 64], removal [71], and the content-preserved process [4, 27].”
Media Forensics and DeepFakes: An Overview (2020, background): “In [155], [156], [157] these concepts are exploited to extract a camera-model fingerprint, called noiseprint, similar to a PRNU-based device fingerprint.”
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (2018, methodology): “) during each image acquisition procedure [24].”
Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations (2019, methodology): “Recent statistical methods form statistical fingerprints on the residuals of an image to detect manipulations [11, 6, 7], validate noise priors from metadata [14], or learn specific manipulation traces, such as recoloring [3] or recompression [28].”
On The Detection of Synthetic Images Generated by Diffusion Models (2022, methodology): “In this work we use the same procedure, using the denoising filter proposed in [28], which proved already successful for camera fingerprint extraction [29].”
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection (2018, methodology): “To avoid any form of polarization on the training-set, recent approaches have adopted Siamese networks to train couples of patches [20, 12].”
ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Features (2019, methodology): “These clues include JPEG compression artifacts [25, 30, 5], edge inconsistencies [39, 53], noise pattern [33, 49, 20], color consistency [21], visual similarity [44, 45, 46], EXIF consistency [28], and camera model [14, 13].”