Image forgery detection

By Hany Farid. IEEE Signal Processing Magazine, 2009

922 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Law

View Paper: https://www.semanticscholar.org/paper/b437e19083a6f50d4eed462ce234a727003d5c7a

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

An Overview on Image Forensics (2013, background): “e technology, de�ned multimedia forensics [13–15], relies on the observation that each phase of the image history, from the acquisition process, to its storing in a compressed format, to any post processing operation leaves a distinctive trace on the data, as a sort of digital �ngerprint.”
Generalizing Face Forgery Detection with High-frequency Features (2021, background): “Though image tampering detection has been investigated for a long time, those conventional detectors [16, 39] cannot handle the detection of face forgery well.”
Deep learning for deepfakes creation and detection: A survey (2019, methodology): “Experimental results show the superior performance of the proposed method against its competing methods such as those introduced in [79]–[82].”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, background): “However, most of the features considered in traditional fake detection methods are highly dependent on the specific training scenario, being therefore not robust against unseen conditions [6], [8], [16].”
Exposing photo manipulation with inconsistent shadows (2013, positive): “@c2013 ACM 0730-0301/2013/06-ART28 $15.00 DOI: http://dx.doi.org/10.1145/2487228.2487236 forensics has emerged to help restore some trust in digital photographs [Farid 2009].”
Digital image forgery detection using passive techniques: A survey (2013, methodology): “Several surveys have been published on image forgery detection: Rocha et al. (2011), Farid (2009a), Mahdian and Saic (2010), Lanh et al. (2007a), Luo et al. (2007a), Mahdian and Saic (2008a), Ng et al. (2006), Sencar and Memon (2008), Zhang et al. (2008a), Bayram et al. (2008a) and Redi et al.…”
Deep Learning for Deepfakes Creation and Detection (2019, methodology): “Experimental results show the superior performance of the proposed method against its competing methods such as those introduced in [69–72].”
PhotoProof: Cryptographic Image Authentication for Any Set of Permissible Transformations (2016, background): “thumbnails embedded in the image file header [30], or in digital artifacts (see [16] for a survey), but in general this can be time-consuming and unreliable.”
Exposing photo manipulation with inconsistent reflections (2012, methodology): “This forensic technique adds to a growing body of forensic analyses [Farid 2009] that, combined, promise to make it increasingly more dif.cult to create a compelling and undetectable forgery.”
Detecting GAN generated Fake Images using Co-occurrence Matrices (2019, methodology): “Several methods have been proposed in the area of image forensics over the past years [25, 26, 27, 28, 29].”
Distinguishing computer graphics from natural images using convolution neural networks (2017, background): “A large part of the current research focuses on the detection of image splicing, copy-past or camera identification [1].”
Media Forensics and DeepFakes: An Overview (2020, background): “In fact, research in multimedia forensics has been going on for at least 15 years [1], [2], and is receiving ever growing attention, not”