Your Text Encoder Can Be An Object-Level Watermarking Controller
Year: 2025
Type: preprint
Abstract: Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models (LDMs). By only fine-tuning text token embeddings $W_*$, we enable watermarking in selected objects or parts of the image, offering greater flexibility compared to traditional full-image watermarking. Our method leverages the text encoder's compatibility across various LDMs, allowing plug-and-play integration for different LDMs. Moreover, introducing the watermark early in the encoding stage improves robustness to adversarial perturbations in later stages of the pipeline. Our approach achieves $99\%$ bit accuracy ($48$ bits) with a $10^5 \times$ reduction in model parameters, enabling efficient watermarking.
Source: arXiv (Cornell University)
Authors: Devulapally, Naresh Kumar, Huang, Mingzhen, Asnani, Vishal, Agarwal, Shruti, Lyu, Siwei, Lokhande, Vishnu Suresh
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6948286083
Cites:
Cited by:
Related to: