ProMark: Proactive Diffusion Watermarking for Causal Attribution

arXiv:2403.09914v1 Announce Type: new
Abstract: 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 …

abstract arxiv attribution capability causal creative creatives cs.cv diffusion genai generative images prompts recognition through training type via watermarking workflows