用隐式水印保护创意写作版权，防止AI模仿
Protecting Creative Writing Copyright against AI Imitation via Implicit Watermarking
- 将创作精髓分解为五个维度，提取凝练特征
- 98%以上准确率，误报率低，不修改原文
- 适合版权方、出版机构、创作者使用
大型语言模型（LLMs）通过上下文学习和微调实现强大知识注入，但也带来高价值创意作品被未经授权模仿的风险。现有版权保护技术多集中于视觉媒体，创意写作的保护仍属空白。本文研究新挑战：验证AI生成文本是否未经许可继承了受保护作品的创作本质。提出WIND（Watermarking via Implicit and Non-disruptive Disentanglement）零水印框架，构建可验证的隐式创作签名。WIND将创作本质分解为五个互补维度，利用基于LLM的实例界定机制提取受保护创作特征的紧凑表示。通过解耦创作相关信息与无关文本变化，将这些表示映射到紧凑水印空间，不修改原始文本。大量实验表明，WIND在多种AI模仿场景下实现超过98%的F1分数，显著优于现有水印与文本分类方法，同时保持低误报率。
原文摘要 · Abstract (English)
Large language models (LLMs) enable powerful knowledge injection through approaches such as in-context learning and fine-tuning, but they also introduce new risks of unauthorized imitation of high-value creative works. Existing copyright protection techniques mainly focus on visual media, leaving the protection of creative writing largely unexplored. In this work, we investigate a new challenge: verifying whether AI-generated texts inherit the creative essence of protected works without authorization. We propose WIND (Watermarking via Implicit and Non-disruptive Disentanglement), a zero-watermarking framework that constructs an implicit and verifiable creative signature for copyright verification. WIND decomposes creative essence into five complementary dimensions and leverages an LLM-based instance delimitation mechanism to extract condensed representations of protected creative characteristics. By disentangling creative-specific information from irrelevant textual variations, these representations are mapped into a compact watermark space without modifying the original texts. Extensive experiments demonstrate that WIND achieves over 98\% F1 scores while maintaining low false-positive rates, substantially outperforming existing watermarking and text classification approaches under various AI imitation scenarios.
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。