Not with my name! Inferring artists' names of input strings employed by Diffusion Models
This addresses copyright concerns for artists by providing a method to infer potential unauthorized use of their names in AI-generated images, though it is a preliminary study.
The paper tackles the problem of detecting whether a diffusion model's generated image used a specific artist's name in its input prompt, by using a Siamese Neural Network to compare generated and original artworks, achieving results that serve as a starting point for predicting full input strings.
Diffusion Models (DM) are highly effective at generating realistic, high-quality images. However, these models lack creativity and merely compose outputs based on their training data, guided by a textual input provided at creation time. Is it acceptable to generate images reminiscent of an artist, employing his name as input? This imply that if the DM is able to replicate an artist's work then it was trained on some or all of his artworks thus violating copyright. In this paper, a preliminary study to infer the probability of use of an artist's name in the input string of a generated image is presented. To this aim we focused only on images generated by the famous DALL-E 2 and collected images (both original and generated) of five renowned artists. Finally, a dedicated Siamese Neural Network was employed to have a first kind of probability. Experimental results demonstrate that our approach is an optimal starting point and can be employed as a prior for predicting a complete input string of an investigated image. Dataset and code are available at: https://github.com/ictlab-unict/not-with-my-name .