Skip to yearly menu bar Skip to main content


Poster
in
Workshop: 2nd Workshop on Generative AI and Law (GenLaw ’24)

Protecting Text IP in the Era of LLMs with Robust and Scalable Watermarking

Gregory Kang Ruey Lau · Xinyuan Niu · Hieu Dao · Jiangwei Chen · Chuan Sheng Foo · Bryan Kian Hsiang Low


Abstract:

In this paper, we propose the first training-free framework for robust and scalable text watermarking applicable across multiple text types (e.g., articles, code) and languages, for general as well as LLM text training data provenance. We highlight perspectives on text IP protection, such as using LLMs to enable better IP protection rather than viewing them as just sources of IP infringement, not relying on just major LLM providers, and the benefits of having a general framework that can be easily adapted to defend against new threats.

Chat is not available.