Litcius/Paper detail

A Novel Neural Model based Framework for Detection of GAN Generated Fake Images

Samaksh Agarwal, Nancy Girdhar, Himanshu Raghav

202126 citationsDOI

Abstract

With the advancement in Generative Adversarial Networks (GAN), it has become easier than ever to generate fake images. These images are more realistic and non-discernible by untrained eyes and can be used to propagate fake information on the Internet. In this paper, we propose a novel method to detect GAN generated fake images by using a combination of frequency spectrum of image and deep learning. We apply Discrete Fourier Transform to each of 3 color channels of the image to obtain its frequency spectrum which shows if the image has been upsampled, a common trend in most GANs, and then train a Capsule Network model with it. Conducting experiments on a dataset of almost 1000 images based on Unconditional data modeling (StyleGan2 - ADA) gave results indicating that the model is promising with accuracy over 99% when trained on the state-of-the-art GAN model. In theory, our model should give decent results when trained with one dataset and tested on another.

Topics & Concepts

Computer scienceArtificial intelligenceImage (mathematics)Computer visionArtificial neural networkPattern recognition (psychology)Generative adversarial networkDeep learningDiscrete Fourier transform (general)Fourier transformFourier analysisMathematicsFractional Fourier transformMathematical analysisGenerative Adversarial Networks and Image SynthesisDigital Media Forensic DetectionAdvanced Image Processing Techniques