Exposing GAN-Generated Faces Using Inconsistent Corneal Specular Highlights
Shu Hu,Yuezun Li,Siwei Lyu +2 more
- pp 2500-2504
Reads0
Chats0
TLDR
This paper showed that GAN synthesized faces can be exposed with inconsistent corneal specular highlights between two eyes due to the lack of physical/physiological constraints in the GAN models.Abstract:
Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models. We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN synthesized faces.read more
Citations
More filters
Journal ArticleDOI
Countering Malicious DeepFakes: Survey, Battleground, and Horizon
TL;DR: A comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of deepFake detection, with more than 318 research papers carefully surveyed is provided in this article .
Journal ArticleDOI
DeepFake Detection for Human Face Images and Videos: A Survey
TL;DR: DeepFake as mentioned in this paper is a generative deep learning algorithm that creates or modifies face features in a superrealistic form, in which it is difficult to distinguish between real and fake features.
Book ChapterDOI
Detection of AI-Generated Synthetic Faces
TL;DR: In this article , the authors present the most effective techniques proposed in the literature for the detection of synthetic faces and analyze their rationale, present real-world application scenarios, and compare different approaches in terms of accuracy and generalization ability.
Journal ArticleDOI
Auguring Fake Face Images Using Dual Input Convolution Neural Network
TL;DR: Wang et al. as mentioned in this paper proposed a dual input convolutional neural network (DICNN) model with ten-fold cross validation with an average training accuracy of 99.36 ± 0.62, a test accuracy of 0.08 ±0.64, and a validation accuracy was 99.30 ± 0 .94.
Book ChapterDOI
The Role of IT Background for Metacognitive Accuracy, Confidence and Overestimation of Deep Fake Recognition Skills
Stefan Sütterlin,Ricardo G. Lugo,Torvald F. Ask,Karl Veng,Jonathan Eck,Jonas Fritschi,Muhammed-Talha Özmen,Basil Bärreiter,Benjamin James Knox +8 more
TL;DR: In this paper , the authors proposed a method and metric to detect overconfident individuals in regards to deep fake recognition, which flags individuals overestimating their performance and thus posing a previously unconsidered cybersecurity risk.
References
More filters
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Proceedings ArticleDOI
A Style-Based Generator Architecture for Generative Adversarial Networks
TL;DR: This paper proposed an alternative generator architecture for GANs, borrowing from style transfer literature, which leads to an automatically learned, unsupervised separation of high-level attributes (e.g., pose and identity when trained on human faces) and stochastic variation in the generated images.
Journal ArticleDOI
scikit-image: Image processing in Python
Stefan van der Walt,Johannes L. Schonberger,Juan Nunez-Iglesias,François Boulogne,Joshua D. Warner,Neil Yager,Emmanuelle Gouillart,Tony S. Yu +7 more
TL;DR: The advantages of open source to achieve the goals of the scikit-image library are highlighted, and several real-world image processing applications that use scik it-image are showcased.
Proceedings Article
Progressive Growing of GANs for Improved Quality, Stability, and Variation
TL;DR: Recently, the authors proposed a new training methodology for GANs that grows both the generator and discriminator progressively, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses.
Journal ArticleDOI
Dlib-ml: A Machine Learning Toolkit
TL;DR: dlib-ml contains an extensible linear algebra toolkit with built in BLAS support, and implementations of algorithms for performing inference in Bayesian networks and kernel-based methods for classification, regression, clustering, anomaly detection, and feature ranking.
Related Papers (5)
Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights
Shu Hu,Yuezun Li,Siwei Lyu +2 more