Statistical Tools for Digital Forensics

By Alin C. Popescu, Hany Farid. Information Hiding, 2004

521 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/aa2720bd32bffc142cb1b9ef53523df57f7218af

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

Citations in the corpus

Exposing digital forgeries in color filter array interpolated images (2005, methodology): “We believe that many complementary techniques such as that presented here, and those that we [5], [8], [9], [10] and others [6], [7], [4] develop, will be needed to reliably expose digital forgeries.”
Photo Forensics From Rounding Artifacts (2020, methodology): “A variety of such forensic techniques have been developed based on the JPEG compression format: The quantization values used to quantize the discrete cosine transform (DCT) coeicients are used to identify the recording camera manufacturer and model [16, 22, 23]; anomalies in the distribution of DCT ”
Detection of Double-Compression in JPEG Images for Applications in Steganography (2008, methodology): “By detecting the traces of recompression in individual image segments, we may be able to identify the forged region because the nontampered part of the image will exhibit traces of doublecompression [13], [17].”
Region Duplication Detection Using Image Feature Matching (2010, methodology): “For JPEG images, a double JPEG quantization is usually a telltale sign of tampering operations (including region duplication), and can be detected based on the histograms of quantized DCT coefficients [42], [20].”
Digital camera identification from sensor pattern noise (2006, methodology): “Techniques, such as the one described in [ 16 ], may help us alleviate the computational complexity of brute force searches by retrieving some information about applied geometrical operations.”
Fast, automatic and fine-grained tampered JPEG image detection via DCT coefficient analysis (2009, background): “2(c)) refers to a block in the tampered region or along the synthesis edge and an unchanged block is a block in the unchanged region.”
Photo forensics from JPEG dimples (2017, methodology): “…(DCT) coefﬁcients are used to identify the recording camera manufacturer and model [2]–[4]; anomalies in the distribution of DCT coefﬁcients are used to reveal multiple JPEG compressions [5]–[7]; and artifacts introduced by the JPEG blocking are used to detected localized tampering [8]–[10].”
Digital image forensics via intrinsic fingerprints (2008, methodology): “Using the final camera output , a set of linear equations for all the pixels in each region is obtained and solved to obtain the interpolation coefficients .”
Determining Image Origin and Integrity Using Sensor Noise (2008, methodology): “Recently, numerous methods for detecting digital forgeries were proposed [ 15 ]–[27], [38].”
Media Forensics and DeepFakes: An Overview (2020, methodology): “Local noise analysis has been proposed using statistical tools in the image domain [60], [61] or in the wavelet domain [62].”
An Overview on Image Forensics (2013, unknown): “e concept of DQ effect is analyzed in more detail by Popescu and Farid in [80], where the artifacts introduced by double compression are quanti�ed thanks to a newly proposed statistical model.”
Exposing Digital Forgeries From JPEG Ghosts (2009, unknown): “And, He et. al developed a technique to detect local traces of double JPEG compression [14] (this work expands on a global approach to detecting double compression [15]).”
Image Forgery Localization via Block-Grained Analysis of JPEG Artifacts (2012, background): “The first case will be referred to as aligned double JPEG (A-DJPG) compression, whereas the second case will be referred to as nonaligned double JPEG (NA-DJPG) compression.”
Information Forensics: An Overview of the First Decade (2013, methodology): “By using a technique to blindly obtain estimate an image’s signal-to-noise ratio (SNR), falsified image regions can be identified by searching for localized inconsistencies in an image’s SNR [18].”
The 'Dresden Image Database' for benchmarking digital image forensics (2010, methodology): “The cameras were drawn from only 25 di.erent models to ensure that device-speci.c and model-speci.c characteristics can be disentangled and studied separately, as validated with results in this paper.”
Forensic detection of image manipulation using statistical intrinsic fingerprints (2010, methodology): “Methods for detecting image forgeries have been proposed by detecting local abnormalities in an image's signal-to-noise ratio (SNR) [14].”
Noiseprint: A CNN-Based Camera Model Fingerprint (2018, background): “The observation that the local noise level within an image may help revealing possible manipulations dates back at least to 2004, with the work of Popescu and Farid [25].”
Digital Image Authentication From JPEG Headers (2011, background): “Previous work in detecting double JPEG compression holds some promise to detect any form of image manipulation [20]–[24].”
Image forgery detection (2009, background): “It is this periodicity that the authors in [35] exploited to detect double JPEG compression.”