CredID: Credible Multi-Bit Watermark for Large Language Models Identification

TL;DR

CredID introduces a multi-party watermarking framework for LLMs that enhances credibility, privacy, and multi-vendor identification accuracy through a novel multi-bit watermarking algorithm and open-source toolkit.

Contribution

This work presents a novel multi-party credible watermarking framework and a multi-bit watermarking algorithm for LLMs, improving identification accuracy and privacy preservation.

Findings

Enhanced watermark credibility and efficiency

Successful multi-vendor identification accuracy

Open-source toolkit facilitates research

Abstract

Large Language Models (LLMs) are widely used in complex natural language processing tasks but raise privacy and security concerns due to the lack of identity recognition. This paper proposes a multi-party credible watermarking framework (CredID) involving a trusted third party (TTP) and multiple LLM vendors to address these issues. In the watermark embedding stage, vendors request a seed from the TTP to generate watermarked text without sending the user's prompt. In the extraction stage, the TTP coordinates each vendor to extract and verify the watermark from the text. This provides a credible watermarking scheme while preserving vendor privacy. Furthermore, current watermarking algorithms struggle with text quality, information capacity, and robustness, making it challenging to meet the diverse identification needs of LLMs. Thus, we propose a novel multi-bit watermarking algorithm and an open-source toolkit to facilitate research. Experiments show our CredID enhances watermark credibility and efficiency without compromising text quality. Additionally, we successfully utilized this framework to achieve highly accurate identification among multiple LLM vendors.