In open large language model (LLM) ecosystems, models are frequently adapted across multiple domains and applications, forming multi-stage derivation chains. Consequently, tracking and verifying historical contributions is essential for model provenance and intellectual property protection. However, existing watermarking methods are mainly designed for single-user, one-time embeddings, often fail under repeated model derivation and incremental updates. To address this problem, we propose LineageMark, a multi-user white-box watermarking framework for model derivation chains. The framework encodes watermarks in model parameters using a projection-based approach. Stable carriers are first selected to reduce sensitivity to model changes, each watermark bit is then represented as a projection statistic over these carriers. Additional watermark insertions introduce only bounded perturbations in the projection space, and margin constraints are used to maintain signal integrity. We evaluate the effectiveness of LineageMark in multi-stage model derivation chains. Experimental results show that LineageMark preserves contributor watermarks across multi-stage derivation and supports incremental multi-user watermark insertion. Furthermore, it exhibits robustness against perturbations such as re-watermarking, fine-tuning, quantization, and pruning.

翻译：在开放的大型语言模型生态系统中，模型经常跨多个领域和应用进行适配，形成多阶段衍生链。因此，追踪和验证历史贡献对于模型溯源与知识产权保护至关重要。然而，现有水印方法主要针对单用户一次性嵌入设计，在重复模型衍生和增量更新场景下常常失效。为解决该问题，我们提出LineageMark——一种面向模型衍生链的多用户白盒水印框架。该框架采用基于投影的方法将水印编码至模型参数中。首先选取稳定载体以降低对模型变化的敏感性，随后将每个水印比特表示为这些载体上的投影统计量。额外水印插入仅在投影空间中引入有界扰动，并通过边界约束维持信号完整性。我们在多阶段模型衍生链中评估了LineageMark的有效性。实验表明，LineageMark能在多阶段衍生过程中保留贡献者水印，支持增量式多用户水印插入。此外，它展现出对重水印、微调、量化和剪枝等扰动的鲁棒性。