Detecting digital image manipulations
Systems, devices, methods and instructions are described for detecting GAN generated images. On embodiment involves receiving an images, generating co-occurrence matrices on color channels of the image, generating analysis of the image by using a convolutional neural network trained to analyze image features of the images based on the generated co-occurrence matrices and determining whether the image is a GAN generated image based on the analysis.
1. A method comprising:
receiving, using one or more processors, an image that comprises a plurality of color channels;
generating, using the one or more processors, a plurality of co-occurrence matrices on pixel values of the plurality of color channels of the image;
generating, using the one or more processors, analysis of the image based on the generated plurality of co-occurrence matrices using a convolutional neural network trained to detect images that are generated using a generative adversarial network (GAN); and
classifying, using the one or more processors, the image as an authentic image based on the analysis.
2. The method of claim 1 , wherein the plurality of color channels includes a red channel.
3. The method of claim 1 , wherein the plurality of color channels includes a green channel.
4. The method of claim 1 , wherein the plurality of color channels includes a blue channel.
5. The method of claim 1 , wherein the convolutional neural network is trained on compressed images.
6. The method of claim 1 , wherein the convolutional neural network is trained on a first dataset comprising unpaired image-to-image translations of objects generated using a cycle-consistent GAN framework.
7. The method of claim 1 , wherein the convolutional neural network is trained on a second dataset comprising authentic images and GAN-generated images.
8. A computer system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the computer system to perform operations comprising:
receiving an image that comprises a plurality of color channels;
generating a plurality of co-occurrence matrices on pixel values of the plurality of color channels of the image;
generating analysis of the image based on the generated plurality of co-occurrence matrices using a convolutional neural network trained to detect images that are generated using a generative adversarial network (GAN); and
classifying the image as an authentic image based on the analysis.
9. The computer system of claim 8 , wherein the plurality of color channels includes a red channel.
10. The computer system of claim 8 , wherein the plurality of color channels includes a green channel.
11. The computer system of claim 8 , wherein the plurality of color channels includes a blue channel.
12. The computer system of claim 8 , wherein the convolutional neural network is trained on compressed images.
13. The computer system of claim 8 , wherein the convolutional neural network is trained on a first dataset comprising unpaired image-to-image translations of objects generated using a cycle-consistent GAN framework.
14. The computer system of claim 8 , wherein the convolutional neural network is trained on a second dataset comprising authentic images and GAN-generated images.
15. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform operations comprising:
receiving an image that comprises a plurality of color channels;
generating a plurality of co-occurrence matrices on pixel values of the plurality of color channels of the image;
generating analysis of the image based on the generated plurality of co-occurrence matrices using a convolutional neural network trained to detect images that are generated using a generative adversarial network (GAN); and
classifying the image as an authentic image based on the analysis.
16. The computer-readable storage medium of claim 15 , wherein the plurality of color channels includes a red channel.
17. The computer-readable storage medium of claim 15 , wherein the plurality of color channels includes a green channel.
18. The computer-readable storage medium of claim 15 , wherein the plurality of color channels includes a blue channel.
19. The computer-readable storage medium of claim 15 , wherein the convolutional neural network is trained on compressed images.
20. The computer-readable storage medium of claim 15 , wherein the convolutional neural network is trained on a first dataset comprising unpaired image-to-image translations of objects generated use a cycle-consistent GAN framework.