Is Your Writing Being Mimicked by AI? Unveiling Imitation with Invisible Watermarks in Creative Writing

ZiWei Zhang, Juan Wen, Wanli Peng, Wu Zhengxian, Yinghan Zhou, Xue yiming

Keywords: Implicitly Verifiable Watermark, Creative Writing, Digital Copyright Protection, Disentangling Creative Writing Essence

TL;DR: In this paper, we propose WIND (Watermarking through Implicit, Non-disruptive Disentanglement), a novel verifiable and implicit watermarking scheme designed to protect the originality of creative writing from unauthorized AI imitation.

Abstract: In-Context Learning (ICL) and efficient fine-tuning methods significantly enhance the efficiency of applying Large Language Models (LLMs) to downstream tasks. However, they also raise concerns about the imitation and infringement of authorial creative works. Current copyright protection methods for creative works predominantly focus on visual arts, leaving a critical research gap in the safeguarding of creative writing. In this paper, we propose WIND (Watermarking through Implicit, Non-disruptive Disentanglement), a novel zero-watermarking, verifiable and implicit scheme designed to protect the originality of creative writing from unauthorized AI imitation. Specifically, we decompose creative essence into five key elements, which are extracted utilizing LLMs through a designed instance delimitation mechanism and consolidated into condensed-lists. These lists enable WIND to convert core copyright attributes into verifiable watermarks via implicit encoding within a disentanglement creative space, where 'disentanglement' refers to the separation of creative-specific and creative-irrelevant features. This approach, utilizing implicit encoding, avoids distorting fragile textual content. Extensive experiments demonstrate that WIND effectively verifies creative writing copyright ownership against AI imitation, achieving F1 scores above 98\% and maintaining robust performance under stringent low false-positive rates where existing state-of-the-art text watermarking methods struggle. The code is available in the supplementary materials.

Primary Area: alignment, fairness, safety, privacy, and societal considerations

Submission Number: 12753