Steal My Artworks for Fine-tuning? A Watermarking Framework for Detecting Art Theft Mimicry in Text-to-Image Models

TL;DR

This paper introduces a watermarking framework that embeds detectable marks into artworks to identify unauthorized fine-tuning of text-to-image models mimicking artists' styles, addressing a critical copyright issue.

Contribution

It proposes a novel watermarking method for artworks that can reliably detect model mimicry and unauthorized fine-tuning using stolen data.

Findings

Watermarks can be reliably detected in generated images.

The framework effectively exposes unauthorized mimicry.

Watermark analysis remains robust against attack methods.

Abstract

The advancement in text-to-image models has led to astonishing artistic performances. However, several studios and websites illegally fine-tune these models using artists' artworks to mimic their styles for profit, which violates the copyrights of artists and diminishes their motivation to produce original works. Currently, there is a notable lack of research focusing on this issue. In this paper, we propose a novel watermarking framework that detects mimicry in text-to-image models through fine-tuning. This framework embeds subtle watermarks into digital artworks to protect their copyrights while still preserving the artist's visual expression. If someone takes watermarked artworks as training data to mimic an artist's style, these watermarks can serve as detectable indicators. By analyzing the distribution of these watermarks in a series of generated images, acts of fine-tuning mimicry using stolen victim data will be exposed. In various fine-tune scenarios and against watermark attack methods, our research confirms that analyzing the distribution of watermarks in artificially generated images reliably detects unauthorized mimicry.