mlsanityData to 14 Oct 2026

Synthetic Iris Image Databases and Identity Leakage: Risks and Mitigation Strategies

arXiv 2506.02626 ↗First posted 3 Jun 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper presents a comprehensive overview of iris image synthesis methods, which can alleviate the issues associated with gathering large, diverse datasets of biometric data from living individuals, which are considered pivotal for biometric methods development. These methods for synthesizing iris data range from traditional, hand crafted image processing-based techniques, through various iterations of GAN-based image generators, variational autoencoders (VAEs), as well as diffusion models. The potential and fidelity in iris image generation of each method is discussed and examples of inferred predictions are provided. Furthermore, the risks of individual biometric features leakage from the training sets are considered, together with possible strategies for preventing them, which have to be implemented should these generative methods be considered a valid replacement of real-world biometric datasets.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 23 of its 56 references that are in the map. First posted on arXiv 3 Jun 2025.

Builds on

23 of 56 references.

References · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  5. 2017Improved Training of Wasserstein GANscited by 2,235
  6. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  7. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  8. 2023DCFace: Synthetic Face Generation with Dual Condition Diffusion Modelcited by 116
  9. 2020This Face Does Not Exist ... But It Might Be Yours! Identity Leakage in Generative Modelscited by 33
  10. 2019Post-mortem Iris Recognition with Deep-Learning-based Image Segmentationcited by 32
  11. 2018Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognitioncited by 24
  12. 2017Synthetic Iris Presentation Attack using iDCGANcited by 17
11 more
  1. 2020CIT-GAN: Cyclic Image Translation Generative Adversarial Network With Application in Iris Presentation Attack Detectioncited by 16
  2. 2018Iris Recognition After Deathcited by 13
  3. 2018Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GANcited by 9
  4. 2024Privacy-Safe Iris Presentation Attack Detectioncited by 6
  5. 2023Forensic Iris Image Synthesiscited by 5
  6. 2024Synthesizing Iris Images using Generative Adversarial Networks: Survey and Comparative Analysiscited by 5
  7. 2024A Parametric Approach to Adversarial Augmentation for Cross-Domain Iris Presentation Attack Detectioncited by 4
  8. 2023EyePreserve: Identity-Preserving Iris Synthesiscited by 3
  9. 2025AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognitioncited by 3
  10. 2025Iris Recognition for Infantscited by 2
  11. 2025Generating a Biometrically Unique and Realistic Iris Databasecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Multi-domain Image Translative Diffusion StyleGAN for Iris Presentation Attack Detection
  2. 2024DiffFinger: Advancing Synthetic Fingerprint Generation through Denoising Diffusion Probabilistic Models
  3. 2026SCHIGAND: A Synthetic Facial Generation Mode Pipeline
  4. 2024Synthetic Forehead-creases Biometric Generation for Reliable User Verification
  5. 2024Enhancing Fingerprint Image Synthesis with GANs, Diffusion Models, and Style Transfer Techniques
  6. 2023On the Biometric Capacity of Generative Face Models
  7. 2025A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition
  8. 2023GANDiffFace: Controllable Generation of Synthetic Datasets for Face Recognition with Realistic Variations