Prompt Stealing Attacks Against Text-to-Image Generation Models

arXiv:2302.09923v2 Announce Type: replace
Abstract: Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and several modifiers can be time-consuming and costly. In consequence, a trend of trading high-quality prompts on specialized marketplaces has emerged. In this paper, we perform the first study on understanding the threat of a novel attack, namely prompt stealing attack, which aims to …

artwork arxiv attacks called can consuming cs.cr cs.lg descriptions design high image image generation images process prompt prompts quality stealing text trading trend