Photo Forensics

By Hany Farid. 2016

Subfields: Computer Vision and Pattern Recognition

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

CNN-Generated Images Are Surprisingly Easy to Spot… for Now (2019, methodology): “Networks (GANs), have generated a huge amount of public interest and concern, as people worry that we are entering a world where it will be impossible to tell which images are real and which are fake [16]. This issue has started to play a signiﬁcant role in global politics; in one case a video of th”
SafetyNet: Detecting and Rejecting Adversarial Examples Robustly (2017, background): “Current best methods to identify fake images require careful analysis of vanishing points [8], illumination angles [6], and shadows [11] (reviews in [8, 7]).”
Fighting Fake News: Image Splice Detection via Learned Self-Consistency (2018, background): “With only rudimentary editing skills, it is now possible to create realistic image composites [3, 4], fill in large image regions [1, 5, 6], generate plausible video from speech [7, 8], etc.”
Do GANs Leave Artificial Fingerprints? (2018, background): “In recent years, a large number of methods have been proposed to single out fake visual data, relying on their semantic, physical, or statistical inconsistencies [10].”
Protecting World Leaders Against Deep Fakes (2019, background): “There is a large body of literature on image and video forensics [11].”
Two-branch Recurrent Network for Isolating Deepfakes in Videos (2020, background): “Although image forensics has been widely studied for a long time [17], deepfakes is recent technology and thus several orthogonal works have been proposed lately for solving the problem of detecting face manipulations.”
Detecting Photoshopped Faces by Scripting Photoshop (2019, methodology): “cing problem, while we address a more subtle manipulation — facial structure warping. Hand-deﬁned manipulation cues Other image forensics work has proposed to detect fake images using handdeﬁned cues [14]. Early work detected resampling artifacts [28,20] by ﬁnding periodic correlations between nearb”
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (2018, methodology): “is critical to look into effective visual forensics against threats from GANs. While recent state-of-the-art visual forensics techniques demonstrate impressive results for detecting fake visual media [16,53,27,13,22,11,35,67,68,26], they have only focused on semantic, physical, or statistical incons”
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces (2018, unknown): “Surveys on these methods can be found in [24,25].”
Exploiting Visual Artifacts to Expose Deepfakes and Face Manipulations (2019, unknown): “, in recent surveys or books [32, 10].”
Deepfake Video Detection Using Recurrent Neural Networks (2018, methodology): “Both featurebased [35, 16] and CNN-based [18, 19] integrity analysis methods have been explored in the literature.”
ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection (2018, background): “Image manipulation is as old as photography itself [15]; however, with recent advances in machine learning and synthetic image rendering, it has reached unprecedented levels of diffusion and sophistication.”
Photo forensics from JPEG dimples (2017, background): “Within the broad range of photo forensic techniques [1], format-based techniques exploit specific artifacts introduced by the underlying image format and compression scheme.”
Noiseprint: A CNN-Based Camera Model Fingerprint (2018, background): “Driven by these phenomena, in the last decade, a large number of methods have been proposed for forgery detection and localization or camera identiﬁcation [1], [2], [3].”
FaceForensics++: Learning to Detect Manipulated Facial Images (2019, unknown): “Surveys on these methods can be found in [25, 51].”
Media Forensics and DeepFakes: An Overview (2020, background): “Research in multimedia forensics has been going on for at least 15 years [1], [2], and is receiving ever growing attention, not only from the academy, but also from major information”