paper-with-me

홈 › Papers

Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging

2025-11-13 · Qinfeng Li, Miao Pan, Jintao Chen, Fu Teng, Zhiqiang Shen, Ge Su, Hao Peng, Xuhong Zhang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.10712

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks

2026-05-26 · Kevin Kuo, Chhavi Yadav, Virginia Smith arxiv

Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rat…

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

2026-04-10 · Jinqi Luo, Jinyu Yang, Tal Neiman, Lei Fan 외 arxiv

Multimodal Large Language Models (MLLMs) have been shown to be vulnerable to malicious queries that can elicit unsafe responses. Recent work uses prompt engineering, response classification, or finetuning to improve MLLM…

Prompt Engineering

GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling

2025-05-25 · Jialong Zhou, Lichao Wang, Xiao Yang

The emergence of large language models (LLMs) enables the development of intelligent agents capable of engaging in complex and multi-turn dialogues. However, multi-agent collaboration face critical safety challenges, suc…

DecoderHallucination

Building Guardrails for Large Language Models

2024-02-02 · Yi Dong, Ronghui Mu, Gaojie Jin, Yi Qi 외

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrail…

AprielGuard

2025-12-23 · Jaykumar Kasundra, Anjaneya Praharaj, Sourabh Surana, Lakshmi Sirisha Chodisetty 외 arxiv

Safeguarding large language models (LLMs) against unsafe or adversarial behavior is critical as they are increasingly deployed in conversational and agentic settings. Existing moderation tools often treat safety risks (e…