提出防御模型合并窃取的新方法，保护开源大模型不被非法集成。
Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
- 通过破坏模型间线性可连接性，主动阻止未经授权的合并。
- 在保持模型性能几乎不变的情况下，有效抵御合并攻击。
- 适合希望保护模型知识产权的研究者与开发者使用。
模型合并已成为扩展大语言模型的有效技术，通过整合专用专家模型实现能力提升。然而，这也带来了新型威胁：模型合并窃取，即免费搭车者通过未经授权的合并方式利用他人模型。现有防御手段无法同时满足三个关键保护需求：(1) 主动阻止未经授权的合并；(2) 兼容通用开源环境；(3) 实现高安全性且性能损失极小。为此，我们提出 MergeBarrier，一种即插即用的防御机制，通过破坏受保护模型与其同源模型之间的线性模式连通性（LMC），消除有效模型合并所需的低损失路径。大量实验表明，MergeBarrier在几乎无性能损失的前提下，能有效防止模型合并窃取。
原文摘要 · Abstract (English)
Model merging has emerged as an efficient technique for expanding large language models (LLMs) by integrating specialized expert models. However, it also introduces a new threat: model merging stealing, where free-riders exploit models through unauthorized model merging. Unfortunately, existing defense mechanisms fail to provide effective protection. Specifically, we identify three critical protection properties that existing methods fail to simultaneously satisfy: (1) proactively preventing unauthorized merging; (2) ensuring compatibility with general open-source settings; (3) achieving high security with negligible performance loss. To address the above issues, we propose MergeBarrier, a plug-and-play defense that proactively prevents unauthorized merging. The core design of MergeBarrier is to disrupt the Linear Mode Connectivity (LMC) between the protected model and its homologous counterparts, thereby eliminating the low-loss path required for effective model merging. Extensive experiments show that MergeBarrier effectively prevents model merging stealing with negligible accuracy loss.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。