mlsanityData to 14 Oct 2026

AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark

arXiv 2406.00783 ↗First posted 2 Jun 2024cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

AI-generated faces have enriched human life, such as entertainment, education, and art. However, they also pose misuse risks. Therefore, detecting AI-generated faces becomes crucial, yet current detectors show biased performance across different demographic groups. Mitigating biases can be done by designing algorithmic fairness methods, which usually require demographically annotated face datasets for model training. However, no existing dataset encompasses both demographic attributes and diverse generative methods simultaneously, which hinders the development of fair detectors for AI-generated faces. In this work, we introduce the AI-Face dataset, the first million-scale demographically annotated AI-generated face image dataset, including real faces, faces from deepfake videos, and faces generated by Generative Adversarial Networks and Diffusion Models. Based on this dataset, we conduct the first comprehensive fairness benchmark to assess various AI face detectors and provide valuable insights and findings to promote the future fair design of AI face detectors. Our AI-Face dataset and benchmark code are publicly available at https://github.com/Purdue-M2/AI-Face-FairnessBench

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 71 of its 123 references that are in the map. First posted on arXiv 2 Jun 2024.

Builds on

71 of 123 references.

References · 71

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  7. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
38 more
  1. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  2. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  3. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  4. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  5. 2018Datasheets for Datasetscited by 1,386
  6. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  7. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  9. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  10. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  11. 2019Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensicscited by 575
  12. 2020Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Cluescited by 523
  13. 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 490
  14. 2014Learning Face Representation from Scratchcited by 453
  15. 2023DIRE for Diffusion-Generated Image Detectioncited by 390
  16. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
  17. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
  18. 2022On the detection of synthetic images generated by diffusion modelscited by 283
  19. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 262
  20. 2020DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detectioncited by 254
  21. 2021Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domaincited by 244
  22. 2023UCF: Uncovering Common Features for Generalizable Deepfake Detectioncited by 180
  23. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  24. 2023DeepfakeBench: A Comprehensive Benchmark of Deepfake Detectioncited by 166
  25. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
  26. 2021Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implicationscited by 128
  27. 2023Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detectioncited by 127
  28. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 120
  29. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  30. 2019Fairness risk measurescited by 85
  31. 2021Towards Measuring Fairness in AI: the Casual Conversations Datasetcited by 80
  32. 2024Detecting Multimedia Generated by Large AI Models: A Surveycited by 76
  33. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  34. 2022CORE: Consistent Representation Learning for Face Forgery Detectioncited by 74
  35. 2024Preserving Fairness Generalization in Deepfake Detectioncited by 70
  36. 2023Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Imagescited by 66
  37. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  38. 2020Analysis of Gender Inequality In Face Recognition Accuracycited by 47

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 14; 2026: 10.

28 papers.

Sort:

By area:

  1. 2025LEGION: Learning to Ground and Explain for Synthetic Image Detectioncited by 65
  2. 2024Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuningcited by 59
  3. 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Modelscited by 12
  4. 2024Evolving from Single-modal to Multi-modal Facial Deepfake Detection: Progress and Challengescited by 6
  5. 2025Improving Generalization of Medical Image Registration Foundation Modelcited by 6
  6. 2025Preserving AUC Fairness in Learning with Noisy Protected Groupscited by 6
  7. 2025Robust AI-Generated Face Detection with Imbalanced Datacited by 5
  8. 2025LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editingcited by 5
  9. 2025Robust Fairness Vision-Language Learning for Medical Image Analysiscited by 4
  10. 2025Rethinking Individual Fairness in Deepfake Detectioncited by 4
  11. 2025Fit for Purpose? Deepfake Detection in the Real Worldcited by 4
  12. 2024OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variationscited by 2
16 more
  1. 2025Fine-Grained DINO Tuning with Dual Supervision for Face Forgery Detectioncited by 1
  2. 2026From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tamperingcited by 1
  3. 2026Detecting AI-Generated Video: A Vision-Language Dual-View Surveycited by 1
  4. 2024Revisiting Face Forgery Detection: From Facial Representation to Forgery Detectioncited by 0
  5. 2025LAMM-ViT: AI Face Detection via Layer-Aware Modulation of Region-Guided Attentioncited by 0
  6. 2025Reliable and Reproducible Demographic Inference for Fairness in Face Analysiscited by 0
  7. 2025SynthGuard: An Open Platform for Detecting AI-Generated Multimedia with Multimodal LLMscited by 0
  8. 2025Are Detectors Fair to Indian IP-AIGC? A Cross-Generator Studycited by 0
  9. 2026Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detectioncited by 0
  10. 2026Skin Tone in the Wild: A Dataset and Benchmark for 10-tone MST Classificationcited by 0
  11. 2026Robust Multi-Source Covid-19 Detection in CT Imagescited by 0
  12. 2026Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioningcited by 0
  13. 2026The Calibrated Deepfake Trust Score (CDTS): Competence-Coupled Trust Degradation Across Deepfake Detectorscited by 0
  14. 2026Face-Trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generatorscited by 0
  15. 2026Detecting CSAM Text-to-Image LoRAs From Weightscited by 0
  16. 2026FairForensics: Seeing Expressions and Parsing Demographics via Vision-Language Modeling for Generalizable Fair Deepfake Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Uncovering Bias in Face Generation Models
  2. 2025Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Data
  3. 2024FaceScore: Benchmarking and Enhancing Face Quality in Human Generation
  4. 2023Analyzing Bias in Diffusion-based Face Generation Models
  5. 2026Learning Late, Guiding Early: Timestep-Decoupled Semantic Guidance for Fair Face Generation
  6. 2026Demographic Fairness in Multimodal LLMs: A Benchmark of Gender and Ethnicity Bias in Face Verification
  7. 2025A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition
  8. 2023Limitations of Face Image Generation