Digital camera identification from sensor pattern noise

By Jan Lukás, Jessica J. Fridrich, Miroslav Goljan. IEEE Transactions on Information Forensics and Security, 2006

1,354 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d74e4144c6875ffbbdd6f5ec5ecbeb32d1a5f88b

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 Media Technology

Citations in the corpus

Information Forensics: An Overview of the First Decade (2013, background): “Such unevenness of light sensitivity is referred to as Photo Response NonUniformity (PRNU) [84].”
Using decision fusion of feature selection in digital forensics for camera source model identification (2012, methodology): “When the method of detecting intrinsic hardware artifacts is adopted, artifacts such as pattern noise [18,21,22,26], lens radial distortion [11], chromatic aberration [44] or sensor dust [16] are used as the fingerprint or biometric to identify either the brand/model source or device source.”
Source Camera Identification Using Enhanced Sensor Pattern Noise (2009, background): “Typical image forensics includes source device identification, source device linking, classification of images taken by unknown cameras, integrity verification, authentication, etc.”
Deep learning for deepfakes creation and detection: A survey (2019, background): “Therefore, PRNU is often considered as the fingerprint of digital cameras left in the images by the cameras [105], [106].”
Exposing photo manipulation with inconsistent reflections (2012, background): “…artifacts [Popescu and Farid 2005a; Kirchner and Gloe 2009], color .lter array aberrations [Popescu and Farid 2005b; Kirchner 2010], disturbances of a camera s sensor noise pattern [Lukas et al. 2006; Fridrich 2009], chromatic aberrations [Johnson and Farid 2006; Gloe et al. 2010], Fig.”
Source Generator Attribution via Inversion (2019, methodology): “Whereas traditional image forensics already include powerful techniques applicable to images captured with a wide range of cameras [16, 12, 3, 4, 9], there are relatively fewer options available to forensic analysts operating on synthetic imagery.”
Autoencoder with recurrent neural networks for video forgery detection (2017, background): “It is a powerful tool for source identiﬁcation [15], but also for image forgery detection [16, 17], since it can be applied irrespective of the speciﬁc type of manipulation.”
Leveraging Frequency Analysis for Deep Fake Image Recognition (2020, neutral): “A common approach is steganalysis (Luk´aˇs et al., 2006; Fridrich, 2009; Bestagini et al., 2013), where high-frequency residuals are used to detect manipulations.”
Camera Model Identification Using Convolutional Neural Networks (2018, methodology): “However, software approach works with color filter array (CFA) interpolation artifacts [15], [16], [17] and Sensor Pattern Noise(SPN) [18].”
Digital image forensics: a booklet for beginners (2010, methodology): “Lukas and others [65], propose to analyze pattern noise for camera identification, as it is a unique stochastic characteristic for both CCD and CMOS sensors.”
How Unique Is Your Web Browser? (2010, background): “Cameras [1,2], typewriters [3], and quartz crystal clocks [4,5] are among the devices that can be ? Thanks to my colleagues at EFF for their help with many aspects of this project, especially Seth Schoen, Tim Jones, Hugh D’Andrade, Chris Controllini, Stu Matthews, Rebecca Jeschke and Cindy Cohn; to ”
Deep Learning for Deepfakes Creation and Detection (2019, background): “PRNU is diﬀerent for every digital camera and often considered as the ﬁngerprint of digital images [95,96].”