Duwak: Dual Watermarks in Large Language Models

Chaoyi Zhu, Jeroen Galjaard, Pin-Yu Chen, Lydia Chen


Abstract
As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms. Existing watermark techniques are shown effective in embedding single human-imperceptible and machine-detectable patterns without significantly affecting generated text quality and semantics. However, the efficiency in detecting watermarks, i.e., the minimum number of tokens required to assert detection with significance and robustness against post-editing, is still debatable. In this paper, we propose, Duwak, to fundamentally enhance the efficiency and quality of watermarking by embedding dual secret patterns in both token probability distribution and sampling schemes. To mitigate expression degradation caused by biasing toward certain tokens, we design a contrastive search to watermark the sampling scheme, which minimizes the token repetition and enhances the diversity. We theoretically explain the interdependency of the two watermarks within Duwak. We evaluate Duwak extensively on Llama2 and Vicuna under various post-editing attacks, against four state-of-the-art watermarking techniques and combinations of them. Our results show that Duwak marked text achieves the highest watermarked text quality at the lowest required token count for detection, up to 70% tokens less than existing approaches, especially under post paraphrasing.
Anthology ID:
2024.findings-acl.678
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11416–11436
Language:
URL:
https://aclanthology.org/2024.findings-acl.678
DOI:
10.18653/v1/2024.findings-acl.678
Bibkey:
Cite (ACL):
Chaoyi Zhu, Jeroen Galjaard, Pin-Yu Chen, and Lydia Chen. 2024. Duwak: Dual Watermarks in Large Language Models. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11416–11436, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Duwak: Dual Watermarks in Large Language Models (Zhu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.678.pdf