Papers
arXiv:2509.01548

Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing

Published on Sep 1
Authors:
,
,
,
,

Abstract

MergeLock is an active protection mechanism that disrupts model parameters to prevent unauthorized merging of Transformer-based models, demonstrating over 95% performance degradation in merged models.

AI-generated summary

Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the safety of model merging have emerged. Unauthorized merging may infringe on developers' rights and risk leaking sensitive personal information. Most existing methods focus on detecting whether a merged model originates from a specific source model, but fail to effectively prevent illegal merging. In this paper, we propose MergeLock, an active protection mechanism that disrupts model parameters to render them unmergeable, thereby directly preventing unauthorized model merging. Specifically, leveraging the inherent symmetry of the attention mechanism in Transformer-based models, we randomly sample two pairs of invertible matrices and apply them to the Query-Key (QK) and Value-Output (VO) branches. This transformation keeps the model's output unchanged while pushing it away from the shared parameter space of other finetuned models. Extensive experiments across both vision and language tasks demonstrate that MergeLock can degrade the performance of merged models by over 95% when a protected model is involved in most cases, demonstrating its effectiveness. Moreover, we further demonstrate that merged models protected by MergeLock cannot be effectively recovered using low-cost restoration methods, further enhancing robustness against unauthorized merging. The code is available at https://github.com/hetailang/Merge-Lock.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2509.01548 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.01548 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.01548 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.