用平滑相关扰动实现扩散语言模型的保质水印。
SAC-Copula: Quality-Preserving Watermarking for Diffusion Language Models via Smooth Correlated Gumbel Fields
- 基于高斯耦合构建局部相关戈布尔扰动场，适配迭代生成动态。
- 相比独立扰动，显著提升生成质量稳定性，降低困惑度尾部波动。
- 适合需要高保真生成与强可检测性的水印应用，如内容溯源。
为扩散语言模型（DLMs）设计水印机制需兼容迭代并行去掩码过程，而非自回归解码。现有基于采样的水印方法通常注入位置独立同分布的扰动，难以匹配DLM解码动态且损害生成质量。本文提出SAC-Copula，一种基于高斯耦合构造的平滑、局部相关戈布尔扰动场的质量保持型水印方法。进一步开发了基于协方差感知滤波与原生样本校准的SAC感知检测器。机制分析表明，局部相关性降低了潜在扰动的粗糙度，更契合迭代优化过程。在LLaDA上的实验显示，SAC-Copula在生成质量与可检测性间取得更优权衡。对Dream-7B及额外数据集的评估表明，其显著提升了困惑度尾部稳定性，优于独立戈布尔基线，同时保持低误报率可检测性与竞争力的生成质量。额外的标记编辑压力测试进一步验证了水印在同步漂移下的鲁棒性。
原文摘要 · Abstract (English)
Watermarking diffusion language models (DLMs) requires mechanisms compatible with iterative parallel unmasking rather than autoregressive decoding. Existing sampling-based watermarking methods typically inject position-wise i.i.d. perturbations, which can be poorly aligned with DLM decoding dynamics and degrade generation quality. We propose SAC-Copula, a quality-preserving watermarking method for DLMs based on smooth, locally correlated Gumbel perturbation fields constructed via a Gaussian copula. We further develop a SAC-aware detector using covariance-aware filtering and native-sample calibration. Mechanism-level analysis shows that local correlation reduces latent perturbation roughness and better matches iterative refinement dynamics. Experiments on LLaDA show that SAC-Copula achieves a favorable quality-detectability trade-off compared with existing baselines. In particular, further evaluations on Dream-7B and additional datasets show that SAC-Copula substantially improves PPL tail stability over the i.i.d. Gumbel baseline, while maintaining strong low-FPR detectability and competitive overall generation quality. Additional token-edit stress tests further assess watermark robustness under controlled synchronization drift.
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。