mlsanityData to 7 Oct 2026

SynthASpoof: Developing Face Presentation Attack Detection Based on Privacy-friendly Synthetic Data

arXiv 2303.02660 ↗First posted 5 Mar 2023cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Recently, significant progress has been made in face presentation attack detection (PAD), which aims to secure face recognition systems against presentation attacks, owing to the availability of several face PAD datasets. However, all available datasets are based on privacy and legally-sensitive authentic biometric data with a limited number of subjects. To target these legal and technical challenges, this work presents the first synthetic-based face PAD dataset, named SynthASpoof, as a large-scale PAD development dataset. The bona fide samples in SynthASpoof are synthetically generated and the attack samples are collected by presenting such synthetic data to capture systems in a real attack scenario. The experimental results demonstrate the feasibility of using SynthASpoof for the development of face PAD. Moreover, we boost the performance of such a solution by incorporating the domain generalization tool MixStyle into the PAD solutions. Additionally, we showed the viability of using synthetic data as a supplement to enrich the diversity of limited authentic training data and consistently enhance PAD performances. The SynthASpoof dataset, containing 25,000 bona fide and 78,800 attack samples, the implementation, and the pre-trained weights are made publicly available.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 5 Mar 2023.

Builds on

33 of 51 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  4. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  5. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  6. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  7. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  8. 2021Domain Generalization with MixStylecited by 563
  9. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 199
  10. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  11. 2021SynFace: Face Recognition with Synthetic Datacited by 106
  12. 2020Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learningcited by 93
21 more
  1. 2019Regularized Fine-grained Meta Face Anti-spoofingcited by 86
  2. 2014Learn Convolutional Neural Network for Face Anti-Spoofingcited by 80
  3. 2019Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Networkcited by 78
  4. 2019Deep Pixel-wise Binary Supervision for Face Presentation Attack Detectioncited by 76
  5. 2019Deep Tree Learning for Zero-shot Face Anti-Spoofingcited by 73
  6. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 68
  7. 2022SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Datacited by 63
  8. 2018A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofingcited by 51
  9. 2022Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectorscited by 47
  10. 2020Revisiting Pixel-Wise Supervision for Face Anti-Spoofingcited by 45
  11. 2021Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detectioncited by 43
  12. 2021Detection and Continual Learning of Novel Face Presentation Attackscited by 33
  13. 2022SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Datacited by 30
  14. 2022Unsupervised Face Recognition using Unlabeled Synthetic Datacited by 27
  15. 2021Real Masks and Spoof Faces: On the Masked Face Presentation Attack Detectioncited by 20
  16. 2021Learnable Multi-level Frequency Decomposition and Hierarchical Attention Mechanism for Generalized Face Presentation Attack Detectioncited by 18
  17. 2022QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantizationcited by 18
  18. 2022Unsupervised Face Morphing Attack Detection via Self-paced Anomaly Detectioncited by 16
  19. 2022Fairness in Face Presentation Attack Detectioncited by 13
  20. 2021Partial Attack Supervision and Regional Weighted Inference for Masked Face Presentation Attack Detectioncited by 10
  21. 2021Myope Models -- Are face presentation attack detection models short-sighted?cited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 4; 2025: 2; 2026: 3.

17 papers.

Sort:

By area:

  1. 2023IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Modelscited by 72
  2. 2023Synthetic Data for Face Recognition: Current State and Future Prospectscited by 38
  3. 2024Generative AI for Synthetic Data Generation: Methods, Challenges and the Futurecited by 31
  4. 2023Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognitioncited by 27
  5. 2023ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generationcited by 22
  6. 2025FoundPAD: Foundation Models Reloaded for Face Presentation Attack Detectioncited by 14
  7. 2023Bias and Diversity in Synthetic-based Face Recognitioncited by 11
  8. 2023Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statisticscited by 7
  9. 2023Are Explainability Tools Gender Biased? A Case Study on Face Presentation Attack Detectioncited by 6
  10. 2024Privacy-Safe Iris Presentation Attack Detectioncited by 6
  11. 2023SynFacePAD 2023: Competition on Face Presentation Attack Detection Based on Privacy-aware Synthetic Training Datacited by 5
  12. 2024Synthesizing Iris Images using Generative Adversarial Networks: Survey and Comparative Analysiscited by 5
5 more
  1. 2025A Multi-domain Image Translative Diffusion StyleGAN for Iris Presentation Attack Detectioncited by 2
  2. 2026Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmarkcited by 1
  3. 2024Sustainable Self-evolution Adversarial Trainingcited by 0
  4. 2026LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detectioncited by 0
  5. 2026Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detectioncited by 0