mlsanityData to 7 Oct 2026

This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces

arXiv 2107.06018 ↗First posted 13 Jul 2021cs.CV cs.AIcited by 25

Not on the map. Why?

Abstract (arXiv)

Recently, generative adversarial networks (GANs) have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website small url http://thispersondoesnotexist.com, taunts users with GAN generated images that seem too real to believe. On the other hand, GANs do leak information about their training data, as evidenced by membership attacks recently demonstrated in the literature. In this work, we challenge the assumption that GAN faces really are novel creations, by constructing a successful membership attack of a new kind. Unlike previous works, our attack can accurately discern samples sharing the same identity as training samples without being the same samples. We demonstrate the interest of our attack across several popular face datasets and GAN training procedures. Notably, we show that even in the presence of significant dataset diversity, an over represented person can pose a privacy concern.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 13 Jul 2021.

Builds on

21 of 32 references.

References · 21

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  5. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  6. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  7. 2016Least Squares Generative Adversarial Networkscited by 1,000
  8. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  9. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  10. 2017Wasserstein GANcited by 635
  11. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  12. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
9 more
  1. 2018Assessing Generative Models via Precision and Recallcited by 401
  2. 2018Deep Face Recognition: A Surveycited by 275
  3. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  4. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 199
  5. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 165
  6. 2017Machine Learning Models that Remember Too Muchcited by 165
  7. 2017Optimizing the Latent Space of Generative Networkscited by 157
  8. 2019Detecting Overfitting of Deep Generative Networks via Latent Recoverycited by 44
  9. 2018Performing Co-Membership Attacks Against Deep Generative Modelscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 6; 2024: 6; 2025: 4; 2026: 2.

25 papers.

Sort:

By area:

  1. 2022Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Modelscited by 418
  2. 2023Understanding and Mitigating Copying in Diffusion Modelscited by 205
  3. 2023On Memorization in Diffusion Modelscited by 122
  4. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
  5. 2023Membership Inference Attacks against Synthetic Data through Overfitting Detectioncited by 66
  6. 2021Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergencecited by 54
  7. 2024Erasing Undesirable Influence in Diffusion Modelscited by 52
  8. 2024A Geometric Framework for Understanding Memorization in Generative Modelscited by 40
  9. 2023A Pathway Towards Responsible AI Generated Contentcited by 38
  10. 2022M^4I: Multi-modal Models Membership Inferencecited by 30
  11. 2022Does CLIP Know My Face?cited by 19
  12. 2024Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Modelscited by 12
13 more
  1. 2024Frame by Familiar Frame: Understanding Replication in Video Diffusion Modelscited by 11
  2. 2024A Survey on Responsible Generative AI: What to Generate and What Notcited by 8
  3. 2024U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AIcited by 7
  4. 2025The Vendiscope: An Algorithmic Microscope For Data Collectionscited by 5
  5. 2023Discriminative Adversarial Privacy: Balancing Accuracy and Membership Privacy in Neural Networkscited by 4
  6. 2023SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmarkcited by 3
  7. 2021MixSyn: Learning Composition and Style for Multi-Source Image Synthesiscited by 2
  8. 2026Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusioncited by 1
  9. 2021Self-supervised denoising for massive noisy imagescited by 0
  10. 2025Redistribute Ensemble Training for Mitigating Memorization in Diffusion Modelscited by 0
  11. 2025GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Facescited by 0
  12. 2025Generative AI in Collaborative Academic Report Writing: Advantages, Disadvantages, and Ethical Considerationscited by 0
  13. 2026NAMESAKES: Probing Identity Memorization in Text-to-Image Modelscited by 0