Skip to content
conftrace_

prompt stealing

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

belief manipulation (1) vision-language model (1) diffusion model (1) black-box attack (1) adversarial attack (1) text-to-image generation (1) data poisoning (1) reinforcement learning (1)

Papers

PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and VLM-Guided Optimization CVPR 2026 Persistent Pre-training Poisoning of LLMs ICLR 2025