Generative AI (GenAI) is transforming creative workflows through the capability to synthesize
and manipulate images via high-level prompts. Yet creatives are not well supported to
receive recognition or reward for the use of their content in GenAI training. To this end we
propose ProMark a causal attribution technique to attribute a synthetically generated image
to its training data concepts like objects motifs templates artists or styles. The concept
information is proactively embedded into the input training images using imperceptible …

We investigate the application of dual watermarks, each positioned on opposing sides of the
image. This exploration raises a pivotal query:“Is the spatial positioning of watermarks
critical to the performance?” To answer this, we ablate four distinct watermark configurations.
As shown in Tab. 1, there is a consistent performance across all watermark placements (left,
right, top, bottom), thereby substantiating the spatial robustness of ProMark in watermark
positioning.