Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Mingzhe, Zhang, Renhao, Wen, Zhiyang, Pan, Siqi, da Silva, Bruno Castro, Zhai, Juan, Ma, Shiqing
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models
by: Li, Mingzhe, et al.
Published: (2025)

Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models
by: Zhao, Shiqian, et al.
Published: (2025)

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models
by: Zou, Xiaotian
Published: (2025)

PRSA: Prompt Stealing Attacks against Real-World Prompt Services
by: Yang, Yong, et al.
Published: (2024)

Prompt Stealing Attacks Against Text-to-Image Generation Models
by: Shen, Xinyue, et al.
Published: (2023)

Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback
by: Chaudhari, Shreyas, et al.
Published: (2025)

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs
by: Jeong, Hyejun, et al.
Published: (2024)

Surrogate Learning in Meta-Black-Box Optimization: A Preliminary Study
by: Ma, Zeyuan, et al.
Published: (2025)

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
by: Wu, Yurong, et al.
Published: (2025)

An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
by: Jiang, Weipeng, et al.
Published: (2024)

Can't Hide Behind the API: Stealing Black-Box Commercial Embedding Models
by: Tamber, Manveer Singh, et al.
Published: (2024)

Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts
by: Mächtle, Felix, et al.
Published: (2025)

Reinforced In-Context Black-Box Optimization
by: Song, Lei, et al.
Published: (2024)

Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection
by: Li, Mingzhe, et al.
Published: (2026)

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study
by: Wang, Zihan, et al.
Published: (2026)

MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization
by: Ma, Zeyuan, et al.
Published: (2025)

RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments
by: Pan, Enze
Published: (2026)

Prompt Fuzzing for Fuzz Driver Generation
by: Lyu, Yunlong, et al.
Published: (2023)

FuzzBox: Blending Fuzzing into Emulation for Binary-Only Embedded Targets
by: Cesarano, Carmine, et al.
Published: (2025)

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation
by: Gharami, Kanchon, et al.
Published: (2025)

GaussEdit: Adaptive 3D Scene Editing with Text and Image Prompts
by: Shu, Zhenyu, et al.
Published: (2025)

Dynamic Prompt Optimizing for Text-to-Image Generation
by: Mo, Wenyi, et al.
Published: (2024)

Gray-Box Fuzzing in Local Space
by: Jonáš, Martin, et al.
Published: (2025)

JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits
by: Pan, Minzhou, et al.
Published: (2024)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

Calibrate-Extrapolate: Rethinking Prevalence Estimation with Black Box Classifiers
by: Wu, Siqi, et al.
Published: (2024)

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
by: Chu, Jaewon, et al.
Published: (2025)

Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
by: Liu, Shiyan, et al.
Published: (2026)

WhisperFuzz: White-Box Fuzzing for Detecting and Locating Timing Vulnerabilities in Processors
by: Borkar, Pallavi, et al.
Published: (2024)

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
by: Li, Xinfeng, et al.
Published: (2025)

Document Optimization for Black-Box Retrieval via Reinforcement Learning
by: Uzan, Omri, et al.
Published: (2026)

Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
by: Goudet, Olivier, et al.
Published: (2025)

Stealing User Prompts from Mixture of Experts
by: Yona, Itay, et al.
Published: (2024)

Stealix: Model Stealing via Prompt Evolution
by: Zhuang, Zhixiong, et al.
Published: (2025)

Adaptive Prompt Elicitation for Text-to-Image Generation
by: Wen, Xinyi, et al.
Published: (2026)

Inference-Aware Prompt Optimization for Aligning Black-Box Large Language Models
by: Mahmud, Saaduddin, et al.
Published: (2025)

Evaluating the Effectiveness of Black-Box Prompt Optimization as the Scale of LLMs Continues to Grow
by: Zhou, Ziyu, et al.
Published: (2025)

PSM: Prompt Sensitivity Minimization via LLM-Guided Black-Box Optimization
by: Jawad, Huseein, et al.
Published: (2025)

Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
by: Zhang, Gehao, et al.
Published: (2025)

DREAM: Debugging and Repairing AutoML Pipelines
by: Zhang, Xiaoyu, et al.
Published: (2023)