Detection of GAN-Generated Fake Images over Social Networks

Marra, Francesco; Gragnaniello, Diego; Cozzolino, Davide; Verdoliva, Luisa

doi:10.1109/mipr.2018.00084

Cited by 290 publications

(191 citation statements)

References 22 publications

Supporting

Mentioning

189

Contrasting

Order By: Relevance

“…Following [4], we conduct experiments on CycleGAN [6] images. We split the dataset based on different semantic categories.…”

Section: A Datasetmentioning

confidence: 99%

“…We randomly select 4,000 images from MSCOCO to train an AutoGAN model. The results of [4]. A-IMG AND A-SPEC ARE MODELS BASED ON AUTOGAN.…”

Section: Training With a Single Semantic Categorymentioning

confidence: 99%

“…To compare with the state-of-the-art methods, we follow the experimental setting detailed in [4] by splitting all the images into 10 folds and perform a leave-one-out test. Following [4], we use a pre-trained DenseNet121 model as base network. The results are shown in Table II.…”

Section: Leave-one-out Settingmentioning

confidence: 99%

See 2 more Smart Citations

Detecting and Simulating Artifacts in GAN Fake Images

Karaman

Chang

2019

2019 IEEE International Workshop on Information Forensics and Security (WIFS)

398

246

View full text Add to dashboard Cite

To detect GAN generated images, conventional supervised machine learning algorithms require collection of a number of real and fake images from the targeted GAN model. However, the specific model used by the attacker is often unavailable. To address this, we propose a GAN simulator, AutoGAN, which can simulate the artifacts produced by the common pipeline shared by several popular GAN models. Additionally, we identify a unique artifact caused by the up-sampling component included in the common GAN pipeline. We show theoretically such artifacts are manifested as replications of spectra in the frequency domain and thus propose a classifier model based on the spectrum input, rather than the pixel input. By using the simulated images to train a spectrum based classifier, even without seeing the fake images produced by the targeted GAN model during training, our approach achieves state-of-the-art performances on detecting fake images generated by popular GAN models such as CycleGAN.

show abstract

“…Following [4], we conduct experiments on CycleGAN [6] images. We split the dataset based on different semantic categories.…”

Section: A Datasetmentioning

confidence: 99%

“…We randomly select 4,000 images from MSCOCO to train an AutoGAN model. The results of [4]. A-IMG AND A-SPEC ARE MODELS BASED ON AUTOGAN.…”

Section: Training With a Single Semantic Categorymentioning

confidence: 99%

See 1 more Smart Citation

Detecting and Simulating Artifacts in GAN Fake Images

Karaman

Chang

2019

2019 IEEE International Workshop on Information Forensics and Security (WIFS)

398

246

View full text Add to dashboard Cite

show abstract

“…The top results they obtained using a combination of residual features [50,9] and deep learning [51]. Similar to [36], the authors in [38] compute the residuals of high pass filtered images and then extract co-occurrence matrices on these residuals, which are then concatenated to form a feature vector that can distinguish real from fake GAN images. In contrast to these approaches, our approach does not need any image resid-uals to be computed.…”

Section: Related Workmentioning

confidence: 99%

Detecting GAN generated Fake Images using Co-occurrence Matrices

Nataraj¹,

Mohammed²,

Manjunath³

et al. 2019

203

169

View full text Add to dashboard Cite

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.

show abstract

“…Approaches based on convolutional neural networks have proven to be very effective. Several architectures have been proposed so far [14], [15], [16] showing a very good accuracy in detecting GAN-generated images, even after compression. The main problem is that new GAN architectures for generating synthetic data are proposed by the day, requiring the detector to be either re-trained on larger and larger training sets, or fine-tuned on them.…”

Section: Introductionmentioning

confidence: 99%

Incremental learning for the detection and classification of GAN-generated images

Marra

Saltori

Boato

et al. 2019

2019 IEEE International Workshop on Information Forensics and Security (WIFS)

Self Cite

115

View full text Add to dashboard Cite

Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new opportunities for the creative industry but, at the same time, new scary scenarios where such content can be maliciously misused. Therefore, it is essential to develop innovative methodologies to automatically tell apart real from computer generated multimedia, possibly able to follow the evolution and continuous improvement of data in terms of quality and realism. In the last few years, several deep learning-based solutions have been proposed for this problem, mostly based on Convolutional Neural Networks (CNNs). Although results are good in controlled conditions, it is not clear how such proposals can adapt to realworld scenarios, where learning needs to continuously evolve as new types of generated data appear. In this work, we tackle this problem by proposing an approach based on incremental learning for the detection and classification of GAN-generated images. Experiments on a dataset comprising images generated by several GAN-based architectures show that the proposed method is able to correctly perform discrimination when new GANs are presented to the network.

show abstract

Detection of GAN-Generated Fake Images over Social Networks

Cited by 290 publications

References 22 publications

Detecting and Simulating Artifacts in GAN Fake Images

Detecting and Simulating Artifacts in GAN Fake Images

Detecting GAN generated Fake Images using Co-occurrence Matrices

Incremental learning for the detection and classification of GAN-generated images

Contact Info

Product

Resources

About