用神经网络自动嵌入水印，提升生成图像版权保护能力
DeepFreqMark: End-To-End Learnable Frequency-Domain Watermarking with Spherical Attack Simulation for Latent Diffusion Models
- 用神经网络代替手工设计水印图案，实现端到端学习
- 在真实攻击下误码率更低，可承载256位信息
- 通过球面插值模拟攻击，训练更高效且不破坏噪声分布
由潜在扩散模型（LDMs）生成的AI图像泛滥，引发版权侵权与虚假信息问题。现有频域水印方法在生成前向初始潜在噪声中嵌入手工几何图案，存在容量有限、模式僵化的问题。本文提出DeepFreqMark，一种端到端可学习的频域水印框架，以神经消息编码器与解码器替代人工图案设计。为克服训练中去噪扩散隐式模型（DDIM）反演带来的计算瓶颈，引入基于球面线性插值（Slerp）的攻击模拟方法，在保持高斯方差不变的前提下直接作用于噪声潜在空间。大量实验表明，DeepFreqMark在真实攻击下显著降低比特误码率（BER），并支持256比特消息容量。源代码已开源。
原文摘要 · Abstract (English)
The proliferation of AI-generated images produced by Latent Diffusion Models (LDMs) has raised critical concerns regarding copyright infringement and misinformation. Although existing frequency-domain watermarking methods embed handcrafted geometric patterns into the initial latent noise prior to generation, they suffer from limited capacity and rigid pattern designs. We propose DeepFreqMark, an end-to-end learnable frequency-domain watermarking framework that replaces manual pattern engineering with a neural message encoder and decoder. To circumvent the computational bottleneck caused by Denoising Diffusion Implicit Model (DDIM) inversion during training, we introduce a Spherical Linear Interpolation (Slerp)-based attack simulation. This approach operates directly on the noise latent while strictly preserving the Gaussian variance. Extensive experiments demonstrate that DeepFreqMark achieves significantly lower Bit Error Rates (BER) than baseline methods under real-world attacks and scales to 256 bits message capacity. Our source code is available at https://github.com/chenhsiu48/DeepFreqMark.
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。