Universally Optimal Watermarking Schemes for LLMs: from Theory to Practice
He, Haiyun, Liu, Yepeng, Wang, Ziqiao, Mao, Yongyi, Bu, Yuheng
–arXiv.org Artificial Intelligence
Large Language Models (LLMs) boosts human efficiency but also poses misuse risks, with watermarking serving as a reliable method to differentiate AI-generated content from human-created text. In this work, we propose a novel theoretical framework for watermarking LLMs. Particularly, we jointly optimize both the watermarking scheme and detector to maximize detection performance, while controlling the worst-case Type-I error and distortion in the watermarked text. Within our framework, we characterize the universally minimum Type-II error, showing a fundamental trade-off between detection performance and distortion. More importantly, we identify the optimal type of detectors and watermarking schemes. Building upon our theoretical analysis, we introduce a practical, model-agnostic and computationally efficient token-level watermarking algorithm that invokes a surrogate model and the Gumbel-max trick. Empirical results on Llama-13B and Mistral-8$\times$7B demonstrate the effectiveness of our method. Furthermore, we also explore how robustness can be integrated into our theoretical framework, which provides a foundation for designing future watermarking systems with improved resilience to adversarial attacks.
arXiv.org Artificial Intelligence
Oct-10-2024
- Country:
- North America > United States (0.28)
- Genre:
- Research Report (1.00)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Technology: