{"ID":2895555,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.08288","arxiv_id":"2507.08288","title":"Invariant-based Robust Weights Watermark for Large Language Models","abstract":"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).","short_abstract":"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 pa...","url_abs":"https://arxiv.org/abs/2507.08288","url_pdf":"https://arxiv.org/pdf/2507.08288v1","authors":"[\"Qingxiao Guo\",\"Xinjie Zhu\",\"Yilong Ma\",\"Hui Jin\",\"Yunhao Wang\",\"Weifeng Zhang\",\"Xiaobing Guo\"]","published":"2025-07-11T03:24:47Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.AI\"]","methods":"[\"Transformer\",\"Large Language Model\",\"Language Model\"]","has_code":false}