Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
arXiv:2109.02167
Abstract
GAN-based techniques that generate and synthesize realistic faces have caused severe social concerns and security problems. Existing methods for detecting GAN-generated faces can perform well on limited public datasets. However, images from existing public datasets do not represent real-world scenarios well enough in terms of view variations and data distributions (where real faces largely outnumber synthetic faces). 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 significantly when facing imbalanced data distributions. To address these shortcomings, we propose a robust, attentive, end-to-end network that can spot GAN-generated faces by analyzing their eye inconsistencies. Specifically, our model learns to identify inconsistent eye components by localizing and comparing the iris artifacts between the two eyes automatically. Our deep network addresses the imbalance learning issues by considering the AUC loss and the traditional cross-entropy loss jointly. Comprehensive evaluations of the FFHQ dataset in terms of both balanced and imbalanced scenarios demonstrate the superiority of the proposed method.
References in corpus (9)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Identification of Deep Network Generated Images Using Disparities in Color Components
- Rethinking the Value of Labels for Improving Class-Imbalanced Learning
- Leveraging Frequency Analysis for Deep Fake Image Recognition
- Detecting GAN-generated Imagery using Color Cues
- Detection, Attribution and Localization of GAN Generated Images