Detecting GAN-generated Imagery using Color Cues
arXiv:1812.08247
Abstract
Image forensics is an increasingly relevant problem, as it can potentially address online disinformation campaigns and mitigate problematic aspects of social media. Of particular interest, given its recent successes, is the detection of imagery produced by Generative Adversarial Networks (GANs), e.g. `deepfakes'. Leveraging large training sets and extensive computing resources, recent work has shown that GANs can be trained to generate synthetic imagery which is (in some ways) indistinguishable from real imagery. We analyze the structure of the generating network of a popular GAN implementation, and show that the network's treatment of color is markedly different from a real camera in two ways. We further show that these two cues can be used to distinguish GAN-generated imagery from camera imagery, demonstrating effective discrimination between GAN imagery and real camera images used to train the GAN.
References in corpus (2)
Cited by in corpus (22)
- Exposing DeepFake Videos By Detecting Face Warping Artifacts
- Leveraging Frequency Analysis for Deep Fake Image Recognition
- Unmasking DeepFakes with simple Features
- Detecting GAN generated Fake Images using Co-occurrence Matrices
- DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
- Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues
- Detecting and Simulating Artifacts in GAN Fake Images
- FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
- Exposing GAN-synthesized Faces Using Landmark Locations
- Detecting Deepfake Videos: An Analysis of Three Techniques
- GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
- SoK: Machine Learning Governance
- Detection, Attribution and Localization of GAN Generated Images
- Improving the Efficiency and Robustness of Deepfakes Detection through Precise Geometric Features
- One-Shot GAN Generated Fake Face Detection
- Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
- AMP: Authentication of Media via Provenance
- Robust Face-Swap Detection Based on 3D Facial Shape Information
- A Method for Identifying Origin of Digital Images Using a Convolution Neural Network
- Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
- Metric Learning for Anti-Compression Facial Forgery Detection
- Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection