# Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights

arXiv: https://arxiv.org/abs/2009.11924 · HTML: https://mlsanity.com/paper/2009.11924/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2020.

## Built on by (most cited first, 30 of 59)

- [AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error](https://mlsanity.com/paper/2401.17879/) (2024)
- [Towards the Detection of Diffusion Model Deepfakes](https://mlsanity.com/paper/2210.14571/) (2022)
- [Preserving Fairness Generalization in Deepfake Detection](https://mlsanity.com/paper/2402.17229/) (2024)
- [Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics](https://mlsanity.com/paper/2403.14077/) (2024)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces](https://mlsanity.com/paper/2109.00162/) (2021)
- [Improving Fairness in Deepfake Detection](https://mlsanity.com/paper/2306.16635/) (2023)
- [PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators](https://mlsanity.com/paper/2304.07361/) (2023)
- [GAN-generated Faces Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2202.07145/) (2022)
- [Robust Attentive Deep Neural Network for Exposing GAN-generated Faces](https://mlsanity.com/paper/2109.02167/) (2021)
- [UnMarker: A Universal Attack on Defensive Image Watermarking](https://mlsanity.com/paper/2405.08363/) (2024)
- [Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images](https://mlsanity.com/paper/2404.12908/) (2024)
- [Characteristics and prevalence of fake social media profiles with AI-generated faces](https://mlsanity.com/paper/2401.02627/) (2024)
- [Characterizing Photorealism and Artifacts in Diffusion Model-Generated Images](https://mlsanity.com/paper/2502.11989/) (2025)
- [From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes](https://mlsanity.com/paper/2504.04827/) (2025)
- [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)
- [PseudoProp: Robust Pseudo-Label Generation for Semi-Supervised Object Detection in Autonomous Driving Systems](https://mlsanity.com/paper/2203.05983/) (2022)
- [AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images](https://mlsanity.com/paper/2404.14244/) (2024)
- [Where Do Deep Fakes Look? Synthetic Face Detection via Gaze Tracking](https://mlsanity.com/paper/2101.01165/) (2021)
- [Masked Conditional Diffusion Model for Enhancing Deepfake Detection](https://mlsanity.com/paper/2402.00541/) (2024)
- [Finding AI-Generated Faces in the Wild](https://mlsanity.com/paper/2311.08577/) (2023)
- [Semantic Contextualization of Face Forgery: A New Definition, Dataset, and Detection Method](https://mlsanity.com/paper/2405.08487/) (2024)
- [An Overview of Recent Work in Media Forensics: Methods and Threats](https://mlsanity.com/paper/2204.12067/) (2022)
- [Adversarial Robustness of AI-Generated Image Detectors in the Real World](https://mlsanity.com/paper/2410.01574/) (2024)
- [Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation](https://mlsanity.com/paper/2304.10249/) (2023)
- [How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection](https://mlsanity.com/paper/2212.14033/) (2022)
- [Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation](https://mlsanity.com/paper/2306.01364/) (2023)
- [Exploiting Facial Relationships and Feature Aggregation for Multi-Face Forgery Detection](https://mlsanity.com/paper/2310.04845/) (2023)
- [Robust AI-Generated Face Detection with Imbalanced Data](https://mlsanity.com/paper/2505.02182/) (2025)

## Abstract (arXiv)

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.