用文本编码器控制图像局部水印，高效且抗干扰。
Your Text Encoder Can Be An Object-Level Watermarking Controller
- 仅微调文本嵌入，实现对象级水印
- 99%准确率，48比特水印，参数减少10万倍
- 兼容多模型，适合版权保护场景
AI生成图像的不可见水印可助力版权保护，实现媒体来源检测与识别。本文提出一种针对T2I潜空间扩散模型（LDMs）的新水印方法，仅通过微调文本标记嵌入 $W_*$，即可在选定物体或图像局部实现水印，相比传统全图水印更具灵活性。该方法利用文本编码器在多种LDM间的兼容性，支持即插即用集成。此外，早期在编码阶段引入水印，增强了对后续流程中对抗扰动的鲁棒性。实验表明，本方法在48比特水印下达到99%位准确率，模型参数量减少 $10^5$ 倍，实现高效水印。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。