Lune

CVPR Findings2026

Verify Claimed Text-to-Image Models Via Boundary-Aware Prompt Optimization

Zidong Zhao, Yihao Huang, Qing Guo, Tianlin Li, Anran Li, Kailong Wang, Jin Song Dong, Geguang Pu

Abstract

As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using official models can mislead users and harm model owners' reputations, making model verification essential to confirm whether an API's underlying model matches its claim. Existing methods address this by using verification prompts generated by official model owners, but the generation relies on multiple reference models for optimization, leading to high computational cost and sensitivity to model selection. To address this problem, we propose a referencefree T2I model verification method called Boundary-aware Prompt Optimization (BPO). It directly explores the intrinsic characteristics of the target model. The key insight is that although different T2I models produce similar outputs for normal prompts, their semantic boundaries in the embedding space (transition zones between two concepts such as "corgi" and "bagel") are distinct. Prompts near these boundaries generate unstable outputs (e.g., sometimes a corgi and sometimes a bagel) on the target model but remain stable on other models. By identifying such boundaryadjacent prompts, BPO captures model-specific behaviors that serve as reliable verification cues for distinguishing T2I models. Experiments on five T2I models and four baselines show that BPO achieves superior verification accuracy.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • High-Resolution Image Synthesis with Latent Diffusion Models cites Zero-Shot Text-to-Image Generation
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on11

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  3. Zero-Shot Text-to-Image GenerationAditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray et al.ICML 2021 · 6,356 citations
  4. Membership Inference Attacks From First PrinciplesNicholas Carlini, Steve Chien, Milad Nasr, Shuang Song et al.S&P 2022 · 1,049 citations
  5. An empirical analysis of compute-optimal large language model trainingJordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya et al.NeurIPS 2022 · 566 citations

Related papers

  1. DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation ModelsZeyang Sha, Zheng Li, Ning Yu, Yang ZhangCCS 2023 · 123 citations
  2. When Anonymity Breaks: Identifying Models Behind Text-to-Image LeaderboardsAli Naseh, Anshuman Suri, Yuefeng Peng, Harsh Chaudhari et al.CVPR 2026
  3. ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation ModelsZeyang Sha, Yicong Tan, Mingjie Li, Michael Backes et al.CCS 2024 · 8 citations
  4. Prompt Stealing Attacks Against Text-to-Image Generation ModelsXinyue Shen, Yiting Qu, Michael Backes, Yang ZhangUSENIX Security 2024 · 65 citations
  5. DOS: Directional Object Separation in Text Embeddings for Multi-Object Image GenerationDongnam Byun, Jungwon Park, Jungmin Ko, Changin Choi et al.AAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines