# Robust Attentive Deep Neural Network for Exposing GAN-generated Faces

arXiv: https://arxiv.org/abs/2109.02167 · HTML: https://mlsanity.com/paper/2109.02167/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 72 references that are in the map.
- First posted on arXiv 5 Sep 2021.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Exposing Deep Fakes Using Inconsistent Head Poses](https://mlsanity.com/paper/1811.00661/) (2018)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [Global Texture Enhancement for Fake Face Detection in the Wild](https://mlsanity.com/paper/2002.00133/) (2020)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Rethinking the Value of Labels for Improving Class-Imbalanced Learning](https://mlsanity.com/paper/2006.07529/) (2020)

## Built on by (most cited first, 28 of 28)

- [Fusing Global and Local Features for Generalized AI-Synthesized Image Detection](https://mlsanity.com/paper/2203.13964/) (2022)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [Improving Fairness in Deepfake Detection](https://mlsanity.com/paper/2306.16635/) (2023)
- [AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark](https://mlsanity.com/paper/2406.00783/) (2024)
- [Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images](https://mlsanity.com/paper/2404.12908/) (2024)
- [Synthesizing Black-box Anti-forensics DeepFakes with High Visual Quality](https://mlsanity.com/paper/2312.10713/) (2023)
- [Open-Eye: An Open Platform to Study Human Performance on Identifying AI-Synthesized Faces](https://mlsanity.com/paper/2205.06680/) (2022)
- [Outlier Robust Adversarial Training](https://mlsanity.com/paper/2309.05145/) (2023)
- [Masked Conditional Diffusion Model for Enhancing Deepfake Detection](https://mlsanity.com/paper/2402.00541/) (2024)
- [Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation](https://mlsanity.com/paper/2304.10249/) (2023)
- [Preserving AUC Fairness in Learning with Noisy Protected Groups](https://mlsanity.com/paper/2505.18532/) (2025)
- [An Explainable Non-local Network for COVID-19 Diagnosis](https://mlsanity.com/paper/2408.04300/) (2024)
- [Data-Driven Fairness Generalization for Deepfake Detection](https://mlsanity.com/paper/2412.16428/) (2024)
- [Robust AI-Generated Face Detection with Imbalanced Data](https://mlsanity.com/paper/2505.02182/) (2025)
- [Hiding Faces in Plain Sight: Defending DeepFakes by Disrupting Face Detection](https://mlsanity.com/paper/2412.01101/) (2024)
- [Robust Fairness Vision-Language Learning for Medical Image Analysis](https://mlsanity.com/paper/2505.03153/) (2025)
- [Rethinking Individual Fairness in Deepfake Detection](https://mlsanity.com/paper/2507.14326/) (2025)
- [Attacking Important Pixels for Anchor-free Detectors](https://mlsanity.com/paper/2301.11457/) (2023)
- [Decoupling Forgery Semantics for Generalizable Deepfake Detection](https://mlsanity.com/paper/2406.09739/) (2024)
- [A Self-Learning Multimodal Approach for Fake News Detection](https://mlsanity.com/paper/2412.05843/) (2024)
- [Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensics](https://mlsanity.com/paper/2504.11686/) (2025)
- [ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces](https://mlsanity.com/paper/2308.00964/) (2023)
- [Decoupling Bias, Aligning Distributions: Synergistic Fairness Optimization for Deepfake Detection](https://mlsanity.com/paper/2511.10150/) (2025)
- [Towards Exploring Fairness in Visual Transformer based Natural and GAN Image Detection Systems](https://mlsanity.com/paper/2310.12076/) (2023)
- [Revisiting Deepfake Detection: Chronological Continual Learning and the Limits of Generalization](https://mlsanity.com/paper/2509.07993/) (2025)
- [SynthGuard: An Open Platform for Detecting AI-Generated Multimedia with Multimodal LLMs](https://mlsanity.com/paper/2511.12404/) (2025)
- [Robust Multi-Source Covid-19 Detection in CT Images](https://mlsanity.com/paper/2604.03320/) (2026)
- [Robust Fair Disease Diagnosis in CT Images](https://mlsanity.com/paper/2604.09710/) (2026)

## Abstract (arXiv)

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.