No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Qi Pang, Shengyuan Hu, Wenting Zheng, Virginia Smith
Abstract
Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that aims to embed information in the output of a model to verify its source, is useful for mitigating the misuse of such AI-generated content. However, we show that common design choices in LLM watermarking schemes make the resulting systems surprisingly susceptible to attack---leading to fundamental trade-offs in robustness, utility, and usability. To navigate these trade-offs, we rigorously study a set of simple yet effective attacks on common watermarking systems, and propose guidelines and defenses for LLM watermarking in practice.
BibTeX
@inproceedings{
pang2024no,
title={No Free Lunch in {LLM} Watermarking: Trade-offs in Watermarking Design Choices},
author={Qi Pang and Shengyuan Hu and Wenting Zheng and Virginia Smith},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=rIOl7KbSkv}
}