AI Paper Atlas

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

PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and VLM-Guided Optimization

Mingzhe Li, Renhao Zhang, Zhiyang Wen, Siqi Pan, Bruno Castro da Silva, Juan Zhai, Shiqing Ma

CVPR 2026 · Image generation › Text-to-image diffusion · approach: T2I evaluation and controllable adapters

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 PromptMiner instead of the best baseline per model on in-the-wild imagesprompt stealing · DiffusionDB in-the-wildCLIP similarity: 0.803 -> 0.863Improved
add potential-based reward shaping to the sparse image-similarity reward in RL phase (ablation)PromptMiner Phase I · training dynamicsimage similarity vs stepsImproved
increase Phase I query budget beyond about 100 on simple prompts (ablation)PromptMiner Phase I · FlickrCLIP similarityNo clear effect
increase Phase I query budget on modifier-rich prompts (ablation)PromptMiner Phase I · LexicaCLIP similarityImproved
increase Phase II query budget (ablation)PromptMiner Phase II · Flickr and LexicaCLIP similarityMixed
apply random noise injection to target imagePromptMiner · Lexica, SD 3.5 MediumCLIP similarity: 0.911 -> 0.903No clear effect
apply puzzle effect to target imagePromptMiner · Lexica, SD 3.5 MediumCLIP similarity: 0.911 -> 0.902No clear effect
overlay textual watermark on target imagePromptMiner · Lexica, SD 3.5 MediumCLIP similarity: 0.911 -> 0.887Hurt
two-phase RL subject plus VLM modifier search versus caption-only BLIP on SBERTPromptMiner · MS COCO, SD 3.5 MediumSBERT: 0.718 -> 0.751Improved
PromptMiner versus PromptStealer on Lexica text alignment with SD v1.5PromptMiner · Lexica, SD v1.5SBERT: 0.563 vs 0.563No clear effect

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