AI RESEARCH

TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery

arXiv CS.CV

ArXi:2602.19019v2 Announce Type: replace Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in complex scenarios where multiple concepts (e.g., an object and an artistic style) are composed within a single image. These methods struggle to disentangle and attribute each concept individually. In this work, we