Robust Attentive Deep Neural Network for Detecting GAN-Generated Faces

Robust Attentive Deep Neural Network for Detecting GAN-Generated Faces

Generative Adversarial Network (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 r...

Full description

Bibliographic Details
Main Authors: Hui Guo, Shu Hu, Xin Wang, Ming-Ching Chang, Siwei Lyu
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
GAN-generated face
fake face detection
iris detection
corneal specular highlights
residual attention network
data imbalance
Online Access:https://ieeexplore.ieee.org/document/9729775/

Internet

https://ieeexplore.ieee.org/document/9729775/

Similar Items