Abstract | ||
---|---|---|
The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as Image-to-Image translations, DeepFakes, and other automated methods have become increasingly popular in creating fake images. In this paper, we propose a novel approach to detect GAN generated fake images using a combination of co-occurrence matrices and deep learning. 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/expressions (StarGAN [2]) show that our approach is promising and achieves more than 99% classification accuracy in both datasets. Further, our approach also generalizes well and achieves good results when trained on one dataset and tested on the other. |
Year | DOI | Venue |
---|---|---|
2019 | 10.2352/issn.2470-1173.2019.5.mwsf-532 | arXiv: Computer Vision and Pattern Recognition |
DocType | Volume | Issue |
Journal | 2019 | 5 |
Citations | PageRank | References |
6 | 0.43 | 25 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lakshmanan Nataraj | 1 | 138 | 10.35 |
Tajuddin Manhar Mohammed | 2 | 31 | 2.97 |
B. S. Manjunath | 3 | 7561 | 783.37 |
Shivkumar Chandrasekaran | 4 | 425 | 40.54 |
Arjuna Flenner | 5 | 30 | 3.98 |
Jawadul H. Bappy | 6 | 75 | 5.64 |
Amit K. Roy-Chowdhury | 7 | 530 | 30.76 |