AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

When Anonymity Breaks: Identifying Models Behind Text-to-Image Leaderboards

Ali Naseh, Anshuman Suri, Yuefeng Peng, Harsh Chaudhari, Alina Oprea, Amir Houmansadr

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use training-free centroid in embedding space instead of trained image classifierdeanonymization attack · 22-way identificationtop-1 accuracy (%): 54.86 -> 90.86Improved
use embedding centroids instead of noise-residual fingerprints (Marra et al.)deanonymization attack · 22-way identificationtop-1 accuracy (%): 24.40 -> 90.86Improved
add text embedding to image-embedding classifier (ablation)embedding MLP classifier · 22-way identificationtop-1 accuracy (%): 43.00 -> 42.50No clear effect
increase reference images per model from 1 to 10 (ablation)centroid attack · 22-way identificationtop-1 accuracy: about 62% -> nearly same as 30 samplesImproved
increase reference images from 10 to 30 per model (ablation)centroid attack · 22-way identificationtop-1 accuracyNo clear effect
use modern image encoder (CLIP-ViT-bigG-14) instead of older encoders (ablation)centroid attack · 22-way identificationtop-1 accuracyImproved
grow candidate pool from 5 to 15 models (ablation)centroid attack · subsets of modelstop-1 accuracy: 96.64% -> 93.86%Hurt
select prompts with high distinguishability score (ablation)centroid attack · prompt controltop-1 accuracy: 0.90 -> 100%Improved
apply adversarial post-processing, eps=2 (ablation)defense · 22-way identificationtop-1 accuracy: 0.90 -> 0.75Improved
apply adversarial post-processing, eps=8 (ablation)defense · 22-way identificationtop-1 accuracy: 0.90 -> 0.46Improved
raise alpha quantile threshold from 0.80 to 0.95 (ablation)threshold classifier · one-vs-rest, target onlyaccuracy: 0.926 -> 0.841Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy