Watermarking technology has gained significant attention due to the increasing importance of intellectual property (IP) rights, particularly with the growing deployment of large language models (LLMs) on billions resource-constrained edge devices. To counter the potential threats of IP theft by malicious users, this paper introduces a robust watermarking scheme without retraining or fine-tuning for transformer models. The scheme generates a unique key for each user and derives a stable watermark value by solving linear constraints constructed from model invariants. Moreover, this technology utilizes noise mechanism to hide watermark locations in multi-user scenarios against collusion attack. This paper evaluates the approach on three popular models (Llama3, Phi3, Gemma), and the experimental results confirm the strong robustness across a range of attack methods (fine-tuning, pruning, quantization, permutation, scaling, reversible matrix and collusion attacks).
@article{arxiv.2507.08288,
title = {Invariant-based Robust Weights Watermark for Large Language Models},
author = {Qingxiao Guo and Xinjie Zhu and Yilong Ma and Hui Jin and Yunhao Wang and Weifeng Zhang and Xiaobing Guo},
journal= {arXiv preprint arXiv:2507.08288},
year = {2025}
}