TokenTrace: Multi-Concept Attribution through Watermarked Token Recovery

TL;DR

TokenTrace introduces a proactive watermarking framework that embeds signatures into diffusion models to enable robust, multi-concept attribution and disentanglement in generated images.

Contribution

It proposes a novel watermarking method that embeds signatures into semantic domains and a query-based retrieval module for multi-concept attribution in generative AI.

Findings

Achieves state-of-the-art performance on multi-concept attribution tasks

Maintains high visual quality and robustness against transformations

Effectively disentangles multiple concepts in generated images

Abstract

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 introduce TokenTrace, a novel proactive watermarking framework for robust, multi-concept attribution. Our method embeds secret signatures into the semantic domain by simultaneously perturbing the text prompt embedding and the initial latent noise that guide the diffusion model's generation process. For retrieval, we propose a query-based TokenTrace module that takes the generated image and a textual query specifying which concepts need to be retrieved (e.g., a specific object or style) as inputs. This query-based mechanism allows the module to disentangle and independently verify the presence of multiple concepts from a single generated image. Extensive experiments show that our method achieves state-of-the-art performance on both single-concept (object and style) and multi-concept attribution tasks, significantly outperforming existing baselines while maintaining high visual quality and robustness to common transformations.