Your Text Encoder Can Be An Object-Level Watermarking Controller

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.

@article{devulapally2025_2503.11945,
  title={ Your Text Encoder Can Be An Object-Level Watermarking Controller },
  author={ Naresh Kumar Devulapally and Mingzhen Huang and Vishal Asnani and Shruti Agarwal and Siwei Lyu and Vishnu Suresh Lokhande },
  journal={arXiv preprint arXiv:2503.11945},
  year={ 2025 }
}