提出可解析控制的隐空间水印框架，提升生成内容版权保护效率与鲁棒性。
ALIEN: Analytic Latent Watermarking for Controllable Generation
- 通过解析推导时间相关调制系数，实现水印嵌入的精准控制
- ALIEN-Q在5项指标上领先现有方法33.1%，ALIEN-R鲁棒性提升14.0%
- 适合关注生成模型版权保护与可控水印技术的研究者
水印技术是保护知识产权和减少滥用的重要手段。现有方法依赖计算成本高昂的启发式优化来迭代优化水印隐变量，以平衡水印鲁棒性与保真度，但存在训练开销大、易陷入局部最优的问题。为此，本文提出首个可解析推导的时间依赖调制系数框架——面向可控生成的解析水印框架（ALIEN）。该框架首次实现了对水印残差扩散过程的解析建模，从而实现可控水印嵌入模式。实验表明，ALIEN-Q在5个质量指标上较当前最优方法提升33.1%，ALIEN-R在15种不同条件下对生成变体与稳定性威胁的鲁棒性提升14.0%。代码将公开于https://anonymous.4open.science/r/ALIEN/。
原文摘要 · Abstract (English)
Watermarking is a technical alternative to safeguarding intellectual property and reducing misuse. Existing methods focus on optimizing watermarked latent variables to balance watermark robustness and fidelity, as Latent diffusion models (LDMs) are considered a powerful tool for generative tasks. However, reliance on computationally intensive heuristic optimization for iterative signal refinement results in high training overhead and local optima entrapment.To address these issues, we propose an \underline{A}na\underline{l}ytical Watermark\underline{i}ng Framework for Controllabl\underline{e} Generatio\underline{n} (ALIEN). We develop the first analytical derivation of the time-dependent modulation coefficient that guides the diffusion of watermark residuals to achieve controllable watermark embedding pattern.Experimental results show that ALIEN-Q outperforms the state-of-the-art by 33.1\% across 5 quality metrics, and ALIEN-R demonstrates 14.0\% improved robustness against generative variant and stability threats compared to the state-of-the-art across 15 distinct conditions. Code can be available at https://anonymous.4open.science/r/ALIEN/.
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。