Detecting GAN-generated Imagery using Color Cues

McCloskey, Scott; Albright, Michael

doi:10.48550/arxiv.1812.08247

Cited by 47 publications

(65 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The work [19] exploited the color disparity between GAN generated images and real images in non-RGB color spaces to classify them. The work [23] also analyzed the color difference between GAN images and real images. However, it is not clear if this method is extensible to inspecting local regions as in the case of DeepFake.…”

Section: Related Work Ai-based Video Synthesis Algorithmsmentioning

confidence: 99%

Exposing DeepFake Videos By Detecting Face Warping Artifacts

Li,

Lyu

2018

Preprint

118

146

View full text Add to dashboard Cite

In this work, we describe a new deep learning based method that can effectively distinguish AI-generated fake videos (referred to as DeepFake videos hereafter) from real videos. Our method is based on the observations that current DeepFake algorithm can only generate images of limited resolutions, which need to be further warped to match the original faces in the source video. Such transforms leave distinctive artifacts in the resulting DeepFake videos, and we show that they can be effectively captured by convolutional neural networks (CNNs). Compared to previous methods which use a large amount of real and DeepFake generated images to train CNN classifier, our method does not need DeepFake generated images as negative training examples since we target the artifacts in affine face warping as the distinctive feature to distinguish real and fake images. The advantages of our method are two-fold: (1) Such artifacts can be simulated directly using simple image processing operations on a image to make it as negative example. Since training a DeepFake model to generate negative examples is time-consuming and resource-demanding, our method saves a plenty of time and resources in training data collection; (2) Since such artifacts are general existed in DeepFake videos from different sources, our method is more robust compared to others. Our method is evaluated on two sets of DeepFake video datasets for its effectiveness in practice.

show abstract

Section: Related Work Ai-based Video Synthesis Algorithmsmentioning

confidence: 99%

Exposing DeepFake Videos By Detecting Face Warping Artifacts

Li,

Lyu

2018

Preprint

118

146

View full text Add to dashboard Cite

show abstract

“…At present, the mainstream DeepFakes detection methods mainly have two directions. The first one is to detect the intra-frame image artifacts introduced during face synthesis or affine transformation, such as inconsistent head pose [46], color cues different from real cameras [27], broken local PRNU patterns [19,24] or detectable differences based on image quality measures (IQM) [13,20]. The other one is to detect inter-frame artifacts in an attempt to discover the artificial temporal inconsistency caused by frame by frame operation.…”

Section: Deepfakes Detection Methodsmentioning

confidence: 99%

FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variations

Sun¹,

Zhang²,

Qiu³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rapid development of generation model, AIbased face manipulation technology, which called Deep-Fakes, has become more and more realistic. This means of face forgery can attack any target, which poses a new threat to personal privacy and property security. Moreover, the misuse of synthetic video shows potential dangers in many areas, such as identity harassment, pornography and news rumors. Inspired by the fact that the spatial coherence and temporal consistency of physiological signal are destroyed in the generated content, we attempt to find inconsistent patterns that can distinguish between real videos and synthetic videos from the variations of facial pixels, which are highly related to physiological information. Our approach first applies Eulerian Video Magnification (EVM) at multiple Gaussian scales to the original video to enlarge the physiological variations caused by the change of facial blood volume, and then transform the original video and magnified videos into a Multi-Scale Eulerian Magnified Spatial-Temporal map (MEMSTmap), which can represent time-varying physiological enhancement sequences on different octaves. Then, these maps are reshaped into frame patches in column units and sent to the vision Transformer to learn the spatio-time descriptors of frame levels. Finally, we sort out the feature embedding and output the probability of judging whether the video is real or fake. We validate our method on the FaceForensics++ and DeepFake Detection datasets. The results show that our model achieves excellent performance in forgery detection, and also show outstanding generalization capability in cross-data domain.

show abstract

“…These methods are explainable in nature. Simple cues such as color difference are used in [33], [34] to distinguish GAN images from the real ones. However, those methods are no longer effective as the GAN methods advance.…”

Section: A Gan-generated Face Detectionmentioning

confidence: 99%

Robust Attentive Deep Neural Network for Detecting GAN-Generated Faces

Hui

Wang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

GAN-based techniques can generate and synthesize realistic faces that cause profound social concerns and security problems. Existing methods for detecting GAN-generated faces can perform well on limited public datasets. However, images from existing datasets do not represent real-world scenarios well enough in terms of view variations and data distributions, where real faces largely outnumber synthetic ones. The state-of-the-art methods do not generalize well in real-world problems and lack the interpretability of detection results. Performance of existing GAN-face detection models degrades accordingly when facing data imbalance issues. To address these shortcomings, we propose a robust, attentive, end-to-end framework that spots GAN-generated faces by analyzing eye inconsistencies. Our model automatically learns to identify inconsistent eye components by localizing and comparing artifacts between eyes. After the iris regions are extracted by Mask-RCNN, we design a Residual Attention Network (RAN) to examine the consistency between the corneal specular highlights of the two eyes. Our method can effectively learn from imbalanced data using a joint loss function combining the traditional cross-entropy loss with a relaxation of the ROC-AUC loss via WMW statistics. Comprehensive evaluations on a newly created FFHQ-GAN dataset in both balanced and imbalanced scenarios demonstrate the superiority of our method.

show abstract

Detecting GAN-generated Imagery using Color Cues

Cited by 47 publications

References 0 publications

Exposing DeepFake Videos By Detecting Face Warping Artifacts

Exposing DeepFake Videos By Detecting Face Warping Artifacts

FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variations

Robust Attentive Deep Neural Network for Detecting GAN-Generated Faces

Contact Info

Product

Resources

About