Functional Subspace Watermarking for Large Language Models

Read full text Summarise with VIRAT
Authors: Zikang Ding, Junhao Li, Suling Wu, Junchi Yao, Hongbo Liu, Lijie Hu
Cited by: 0
References: 26

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably undergo complex distortions during realistic model modifications such as fine-tuning, quantization, or knowledge distillation, making reliable extraction extremely challenging. Despite extensive research on model-side watermarking, existing methods still lack sufficient robustness against parameter-level perturbations. To address this gap, we propose \texttt{\textbf{Functional Subspace Watermarking (FSW)}}, a framework that anchors ownership signals into a low-dimensional functional backbone. Specifically, we first solve a generalized eigenvalue problem to extract a stable functional subspace for watermark injection, while introducing an adaptive spectral truncation strategy to achieve an optimal balance between robustness and model utility. Furthermore, a vector consistency constraint is incorporated to ensure that watermark injection does not compromise the original semantic performance. Extensive experiments across various LLM architectures and datasets demonstrate that our method achieves superior detection accuracy and statistical verifiability under multiple model attacks, maintaining robustness that outperforms existing state-of-the-art (SOTA) methods.

Fields of Study & Subjects

Adversarial Robustness in Machine Learning Advanced Steganography and Watermarking Techniques Physical Unclonable Functions (PUFs) and Hardware Security

Publication details

Journal / source
arXiv (Cornell University)
Publication date
19 March 2026
Language
EN
Document type
Preprint