AI Paper Atlas

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

Automated Red Teaming for Text-to-Image Models through Feedback-Guided Prompt Iteration with Vision-Language Models

Wei Xu, Kangjie Chen, Jiawei Qiu, Yuyang Zhang, Run Wang, Jin Mao, Tianwei Zhang, Lina Wang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 1 citations (OpenAlex)

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 FGPI single-turn instead of ARTFGPI · Lexica seed set (560 prompts), SD 2.1ASR (%): 56.43% -> 77.86%Improved
use FGPI instead of FLIRT for prompt safetyFGPI · Lexica seed set (560 prompts), SD 2.1safe prompt rate (%): 54.64% -> 96.96%Improved
use FGPI multi-turn instead of GrootFGPI · NSFW adversarial prompt set (231 prompts), SD 2.1ASR (%): 55.41% -> 78.35%Improved
use FGPI multi-turn instead of SneakyPromptFGPI · NSFW adversarial prompt set (231 prompts), SD 2.1ASR (%): 62.33% -> 78.35%Improved
use multi-turn instead of single-turn feedback-guide-rewrite (ablation)FGPI · Lexica seed set (560 prompts), SD 2.1ASR (%): 77.86% -> 75.71%No clear effect
use multi-turn instead of single-turn feedback-guide-rewrite (ablation)FGPI · NSFW adversarial prompt set (231 prompts), SD 2.1ASR (%): 72.29% -> 78.35%Improved
add iterative optimization rounds (round 0 to 5) (ablation)FGPI · Seed-free generation, SD 2.1ASR (%): 38.21% -> 88.57%Improved
add iterative optimization rounds (round 0 to 3) (ablation)FGPI · Seed-free generation, DALL-E 3ASR (%): 56.43% -> 85.71%Improved
add iterative optimization rounds (round 0 to 3) (ablation)FGPI · Seed-free generation, DALL-E 3request rejection rate (%): 12.14% -> 6.43%Improved
add iterative optimization rounds (round 0 to 5) (ablation)FGPI · Seed-free generation, SD 2.1safe prompt rate (%): 89.64% -> 97.86%Improved
remove seed prompts (seed-free generation) (ablation)FGPI · Seed-free generation, SD 2.1ASR (%): 77.86% -> 88.57%Improved
transfer prompts from SD 1.5 to SD 2.1FGPI · Transfer attack, source SD 1.5 to target SD 2.1ASR (%): 100.0 -> 72.79Hurt

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