Plug-and-Play Multi-Licensee Robust Watermarking for Mixture-of-Experts LLMs

Mixture-of-Experts (MoE) architectures enable high-capacity large language models (LLMs) with high sparse computation, making them attractive for deployment on private hardware. However, distributing model weights exposes valuable intellectual property (IP) to leakage and unauthorized redistribution, creating an urgent need to both verify model ownership and trace leaked copies to individual licensees. Existing model-watermarking techniques are ill-suited for meeting this need because they are fragile under MoE's dynamic routing or require costly retraining to embed a distinct watermark for each licensee, thus making scalable distribution difficult. To address these challenges, we present PPMoE, the first plug-and-play multi-licensee watermarking framework for MoE LLMs. Rather than training a separate model per user, PPMoE trains a compact set of mergeable incremental weight modules that steer the MoE router toward distinct, mutually compatible routing patterns. During model distribution, the model owner selectively merges unique combinations of these pre-trained, mutually compatible modules into the base model on the fly, embedding a licensee-specific watermark without additional training. PPMoE supports reliable multi-licensee attribution under both white- and black-box threat models. In the white-box setting, attribution is done by inspecting triggered routing decisions or the merged weight modules responsible for these decisions, whereas in the black-box setting, attribution relies on analyzing output token likelihood ratios. Extensive experiments across five state-of-the-art MoE models, seven benchmark datasets, and varying number of licensees show that PPMoE achieves very high attribution accuracy while preserving base model utility and maintaining strong robustness to various adaptive watermark-removal attacks.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23838
Primary Topic
Advanced Steganography and Watermarking Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Plug-and-Play Multi-Licensee Robust Watermarking for Mixture-of-Experts LLMs

Haining Wang, Kang G. Shin, Jianshuo Liu
arXiv (Cornell University)
Advanced Steganography and Watermarking Techniques
preprint

Plug-and-Play Multi-Licensee Robust Watermarking for Mixture-of-Experts LLMs

Haining Wang, Kang G. Shin, Jianshuo Liu
preprint en

Abstract

Mixture-of-Experts (MoE) architectures enable high-capacity large language models (LLMs) with high sparse computation, making them attractive for deployment on private hardware. However, distributing model weights exposes valuable intellectual property (IP) to leakage and unauthorized redistribution, creating an urgent need to both verify model ownership and trace leaked copies to individual licensees. Existing model-watermarking techniques are ill-suited for meeting this need because they are fragile under MoE's dynamic routing or require costly retraining to embed a distinct watermark for each licensee, thus making scalable distribution difficult. To address these challenges, we present PPMoE, the first plug-and-play multi-licensee watermarking framework for MoE LLMs. Rather than training a separate model per user, PPMoE trains a compact set of mergeable incremental weight modules that steer the MoE router toward distinct, mutually compatible routing patterns. During model distribution, the model owner selectively merges unique combinations of these pre-trained, mutually compatible modules into the base model on the fly, embedding a licensee-specific watermark without additional training. PPMoE supports reliable multi-licensee attribution under both white- and black-box threat models. In the white-box setting, attribution is done by inspecting triggered routing decisions or the merged weight modules responsible for these decisions, whereas in the black-box setting, attribution relies on analyzing output token likelihood ratios. Extensive experiments across five state-of-the-art MoE models, seven benchmark datasets, and varying number of licensees show that PPMoE achieves very high attribution accuracy while preserving base model utility and maintaining strong robustness to various adaptive watermark-removal attacks.

arXiv (Cornell University)
Advanced Steganography and Watermarking Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon