Promptly Yours? A Human Subject Study on Prompt Inference in AI-Generated Art

TL;DR

This study examines the ability of humans and AI-human collaborations to infer prompts from AI-generated images in art marketplaces, revealing high but imperfect accuracy and implications for intellectual property security.

Contribution

First to include humans in prompt inference research, assessing their ability to deduce original prompts and improve results through human-AI collaboration.

Findings

Humans can accurately infer prompts from images

Human-AI collaboration improves prompt inference

Original prompts remain more accurate than inferred ones

Abstract

The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts for generating unique artworks. These marketplaces often assert ownership over prompts, claiming them as intellectual property. This paper investigates whether concealed prompts sold on prompt marketplaces can be considered as secure intellectual property, given that humans and AI tools may be able to approximately infer the prompts based on publicly advertised sample images accompanying each prompt on sale. Specifically, our survey aims to assess (i) how accurately can humans infer the original prompt solely by examining an AI-generated image, with the goal of generating images similar to the original image, and (ii) the possibility of improving upon individual human and AI prompt inferences by crafting human-AI combined prompts with the help of a large language model. Although previous research has explored the use of AI and machine learning to infer (and also protect against) prompt inference, we are the first to include humans in the loop. Our findings indicate that while humans and human-AI collaborations can infer prompts and generate similar images with high accuracy, they are not as successful as using the original prompt.