Detecting GAN generated Fake Images using Co-occurrence Matrices

@article{Nataraj2019DetectingGG,
  title={Detecting GAN generated Fake Images using Co-occurrence Matrices},
  author={Lakshmanan Nataraj and Tajuddin Manhar Mohammed and B. S. Manjunath and Shivkumar Chandrasekaran and Arjuna Flenner and Jawadul H. Bappy and Amit K. Roy-Chowdhury},
  journal={ArXiv},
  year={2019},
  volume={abs/1903.06836}
}
The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. [...] Key Method We extract co-occurrence matrices on three color channels in the pixel domain and train a model using a deep convolutional neural network (CNN) framework. Experimental results on two diverse and challenging GAN datasets comprising more than 56,000 images based on unpaired image-to-image translations (cycleGAN [1]) and facial attributes…Expand
Attributing and Detecting Fake Images Generated by Known GANs
TLDR
The frequency domain to attribute and detect fake images generated by a known GAN model is analyzed and a similarity metric on the frequency domain is derived and a new approach for GAN image attribution is developed. Expand
Detection, Attribution and Localization of GAN Generated Images
TLDR
A novel approach to detect, attribute and localize GAN generated images that combines image features with deep learning methods is proposed. Expand
NoiseScope: Detecting Deepfake Images in a Blind Setting
TLDR
This work proposes a blind detection approach called NoiseScope for discovering GAN images among other real images, and examines the limitations of NoiseScope against a variety of countermeasures, observing that NoiseScope holds robust or is easily adaptable. Expand
Detection of GAN-Synthesized Image Based on Discrete Wavelet Transform
TLDR
In this study, a method named fake images discriminator (FID) is proposed, which detects that GAN-synthesized fake images use the strong spectral correlation in the imaging process of natural color images. Expand
Global Texture Enhancement for Fake Face Detection in the Wild
TLDR
A new architecture coined as Gram-Net, which leverages global image texture representations for robust fake image detection and generalizes significantly better in detecting fake faces from GAN models not seen in the training phase and can perform decently in detectingfake natural images. Expand
Identification of deep network generated images using disparities in color components
TLDR
This paper proposes a feature set to capture color image statistics for identifying deep network generated (DNG) images and shows that the DNG images are more distinguishable from real ones in the chrominance components, especially in the residual domain. Expand
T-GD: Transferable GAN-generated Images Detection Framework
TLDR
T-GD achieves high performance on the source dataset by overcoming catastrophic forgetting and effectively detecting state-of-the-art GAN-images with only a small volume of data without any metadata information. Expand
Robust Facial Manipulation Detection via Domain Generalization
TLDR
This paper presents a method to improve the generalization ability of the detection models using one class domain generalization, and takes the fake facial images from multiple domains into the domain discriminator for domain adversarial training. Expand
Detecting GANs and Retouching based Digital Alterations via DAD-HCNN
TLDR
A hierarchical approach termed as DAD-HCNN which performs two-fold task: it differentiates between digitally generated images and digitally retouched images from the original unaltered images, and to increase the explainability of the decision, it also identifies the GAN architecture used to create the image. Expand
Fake Visual Content Detection Using Two-Stream Convolutional Neural Networks
TLDR
The proposed detector has demonstrated significant performance improvement compared to the current state-of-the-art fake content detectors and fusing the frequency and spatial domain streams has also improved generalization of the detector. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 54 REFERENCES
Detection of GAN-Generated Fake Images over Social Networks
The diffusion of fake images and videos on social networks is a fast growing problem. Commercial media editing tools allow anyone to remove, add, or clone people and objects, to generate fake images.Expand
Fake Faces Identification via Convolutional Neural Network
TLDR
This paper proposes a Convolutional Neural Network (CNN) based method to identify fake face images generated by the current best method, and provides experimental evidences to show that the proposed method can achieve satisfactory results with an average accuracy over 99.4%. Expand
Can Forensic Detectors Identify GAN Generated Images?
TLDR
This paper investigates how forensic detectors perform in differentiating between GAN generated images and real images, and considers two kinds of approaches, one is intrusive and the other is non-intrusive, based on whether the GAN architecture is needed for performing detection. Expand
Identification of deep network generated images using disparities in color components
TLDR
This paper proposes a feature set to capture color image statistics for identifying deep network generated (DNG) images and shows that the DNG images are more distinguishable from real ones in the chrominance components, especially in the residual domain. Expand
Detection of Deep Network Generated Images Using Disparities in Color Components
TLDR
The proposed feature set to capture color image statistics for detecting deep network generated (DNG) images is proposed and experimental results show that the proposed method is able to distinguish the DNG images from real ones with high accuracies. Expand
On Detecting GANs and Retouching based Synthetic Alterations
TLDR
A supervised deep learning algorithm using Convolutional Neural Networks (CNNs) to detect synthetically altered images and yields an accuracy of 99.65% on detecting retouching on the ND-IIITD dataset, which outperforms the previous state of the art. Expand
Detecting GAN-generated Imagery using Color Cues
TLDR
It is shown that the network's treatment of color is markedly different from a real camera in two ways, and 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. Expand
A deep learning approach to detection of splicing and copy-move forgeries in images
  • Y. Rao, J. Ni
  • Computer Science
  • 2016 IEEE International Workshop on Information Forensics and Security (WIFS)
  • 2016
TLDR
A new image forgery detection method based on deep learning technique, which utilizes a convolutional neural network to automatically learn hierarchical representations from the input RGB color images to outperforms some state-of-the-art methods. Expand
Detecting Both Machine and Human Created Fake Face Images In the Wild
TLDR
This work proposes neural network based classifiers to detect fake human faces created by both 1) machines and 2) humans and uses ensemble methods to detect GANs-created fake images and employ pre-processing techniques to improve fake face image detection created by humans. Expand
Do GANs Leave Artificial Fingerprints?
TLDR
It is shown that each GAN leaves its specific fingerprint in the images it generates, just like real-world cameras mark acquired images with traces of their photo-response non-uniformity pattern. Expand
...
1
2
3
4
5
...