# NAMESAKES: Probing Identity Memorization in Text-to-Image Models

arXiv: https://arxiv.org/abs/2606.20155 · HTML: https://mlsanity.com/paper/2606.20155/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Designing an Encoder for StyleGAN Image Manipulation](https://mlsanity.com/paper/2102.02766/) (2021)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development](https://mlsanity.com/paper/2108.04308/) (2021)
- [Inserting Anybody in Diffusion Models via Celeb Basis](https://mlsanity.com/paper/2306.00926/) (2023)
- [Towards More Realistic Membership Inference Attacks on Large Diffusion Models](https://mlsanity.com/paper/2306.12983/) (2023)
- [Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models](https://mlsanity.com/paper/2406.02366/) (2024)
- [This Person (Probably) Exists. Identity Membership Attacks Against GAN Generated Faces](https://mlsanity.com/paper/2107.06018/) (2021)
- [Distilling Diversity and Control in Diffusion Models](https://mlsanity.com/paper/2503.10637/) (2025)
- [Towards Fair Face Verification: An In-depth Analysis of Demographic Biases](https://mlsanity.com/paper/2307.10011/) (2023)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models](https://mlsanity.com/paper/2405.14517/) (2024)
- [When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators](https://mlsanity.com/paper/2602.19946/) (2026)
- [MagicNaming: Consistent Identity Generation by Finding a "Name Space" in T2I Diffusion Models](https://mlsanity.com/paper/2412.14902/) (2024)
- [Identity-Focused Inference and Extraction Attacks on Diffusion Models](https://mlsanity.com/paper/2410.10177/) (2024)

## Abstract (arXiv)

Text-to-image (T2I) models generate realistic likenesses of some individuals when prompted with their names, raising privacy concerns. However, distinguishing whether a generated face is memorized or fabricated currently requires ground-truth photos, access to training data, or white-box access to model internals, limiting applicability. We introduce a fully black-box behavioral probe that distinguishes between memorized and unrecognized names, while requiring no reference photos or prior knowledge of training data. To benchmark this task, we present the NAMESAKES dataset of over one thousand names and faces of public figures spanning a wide range of fame levels, along with perturbed, less famous names. Experiments on state-of-the-art T2I models show that our probe substantially predicts identity memorization and separates memorized from unrecognized names, with further insights into differences across model families.