Score: 0

Your Text Encoder Can Be An Object-Level Watermarking Controller

Published: March 15, 2025 | arXiv ID: 2503.11945v1

By: Naresh Kumar Devulapally , Mingzhen Huang , Vishal Asnani and more

Potential Business Impact:

Marks AI pictures so you know they're fake.

Business Areas:
Image Recognition Data and Analytics, Software

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.

Country of Origin
🇺🇸 United States

Page Count
19 pages

Category
Computer Science:
CV and Pattern Recognition