Style Memorization in Text-to-Image Generative Models

While the intended use of generative models is to create novel content, they can generate expressive content on a large scale that closely resembles training data, particularly memorized styles of specific artists, competing with human creators in existing markets. Past research overlooks this type of subtle memorization by focusing on exact/near-exact copies and by failing to account for the inherit difficulty of reproducing atypical semantic properties, like artistic styles. To distinguish expected from unexpected/undesired capabilities, this work proposes ($\tau$, $\lambda$)-memorization that defines an extractable artistic style as memorized if it is sufficiently atypical at the image-level ($\lambda$) and caption-level ($\tau$), as these outlier-properties are inherently difficult to reproduce. Experiments show that the popular general-purpose model Stable Diffusion memorized 34% of artistic styles, producing fake artworks based on non-overly descriptive prompts that enable artist re-identification with visual search, highlighting potential market impact. With adequate thresholds $\tau$ and $\lambda$ to define caption and style atypicality, style memorization is detected with over 20% TPR at 1% FPR, unlike prior work that only achieves TPR as high as FPR. This work shows that atypical artistic styles are more likely to be memorized, particularly underrepresented ones, exposing an underestimation of memorization risks of current frequency-based indicators, thus informing data owners of risks of style memorization and the need for appropriate mitigation strategies.