Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Qinfeng, Pan, Miao, Chen, Jintao, Teng, Fu, Shen, Zhiqiang, Su, Ge, Peng, Hao, Zhang, Xuhong
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
by: Li, Qinfeng, et al.
Published: (2024)

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment
by: Li, Qinfeng, et al.
Published: (2024)

Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
by: Gao, Yilan, et al.
Published: (2026)

BadMerging: Backdoor Attacks Against Model Merging
by: Zhang, Jinghuai, et al.
Published: (2024)

Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging
by: Cong, Tianshuo, et al.
Published: (2024)

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
by: Yuan, Zenghui, et al.
Published: (2025)

Defending Unauthorized Model Merging via Dual-Stage Weight Protection
by: Chen, Wei-Jia, et al.
Published: (2025)

Safeguarding Voice Privacy: Harnessing Near-Ultrasonic Interference To Protect Against Unauthorized Audio Recording
by: McKee, Forrest, et al.
Published: (2024)

Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging
by: Lu, Lin, et al.
Published: (2025)

DistilLock: Safeguarding LLMs from Unauthorized Knowledge Distillation on the Edge
by: Mohanty, Asmita, et al.
Published: (2025)

ExpShield: Safeguarding Web Text from Unauthorized Crawling and LLM Exploitation
by: Liu, Ruixuan, et al.
Published: (2024)

SPARE: Securing Progressive Web Applications Against Unauthorized Replications
by: Talukder, Sajib, et al.
Published: (2025)

Safeguarding LLMs Against Misuse and AI-Driven Malware Using Steganographic Canaries
by: Raz, Md, et al.
Published: (2026)

Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs
by: Li, Jinmin, et al.
Published: (2024)

MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models
by: Yamabe, Shojiro, et al.
Published: (2024)

A UEFI System with SPDM to Protect Against Unauthorized Device Connections
by: de Freitas, Ágatha, et al.
Published: (2026)

Differentially Private Model Merging
by: Yin, Qichuan, et al.
Published: (2026)

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
by: Hao, Shuyang, et al.
Published: (2025)

On Evaluating the Durability of Safeguards for Open-Weight LLMs
by: Qi, Xiangyu, et al.
Published: (2024)

When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion
by: Li, Jiaqing, et al.
Published: (2026)

Shifting-Merging: Secure, High-Capacity and Efficient Steganography via Large Language Models
by: Bai, Minhao, et al.
Published: (2025)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
by: Li, Siyuan, et al.
Published: (2026)

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
by: Yang, Jinluan, et al.
Published: (2024)

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
by: Li, Qinfeng, et al.
Published: (2026)

Encrypted Prompt: Securing LLM Applications Against Unauthorized Actions
by: Chan, Shih-Han
Published: (2025)

MergeGuard: Efficient Thwarting of Trojan Attacks in Machine Learning Models
by: Shabgahi, Soheil Zibakhsh, et al.
Published: (2025)

Merged Bitcoin: Proof of Work Blockchains with Multiple Hash Types
by: Blake, Christopher, et al.
Published: (2026)

Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
by: Wang, Jiawen, et al.
Published: (2025)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
by: Cui, Yingqian, et al.
Published: (2023)

Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
by: Guan, Faqian, et al.
Published: (2024)

WAPITI: A Watermark for Finetuned Open-Source LLMs
by: Chen, Lingjie, et al.
Published: (2024)

Shattering the Echo Chamber: Hidden Safeguards in Manuscripts Against the AI Takeover of Peer Review
by: Ma, Oubo, et al.
Published: (2026)

TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
by: Mo, Yichuan, et al.
Published: (2024)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
by: Zhang, Yucheng, et al.
Published: (2024)

EnTruth: Enhancing the Traceability of Unauthorized Dataset Usage in Text-to-image Diffusion Models with Minimal and Robust Alterations
by: Ren, Jie, et al.
Published: (2024)

LoBAM: LoRA-Based Backdoor Attack on Model Merging
by: Yin, Ming, et al.
Published: (2024)

Large Language Models for Code Analysis: Do LLMs Really Do Their Job?
by: Fang, Chongzhou, et al.
Published: (2023)

Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations
by: Lin, Xun, et al.
Published: (2024)

GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
by: Li, Haoran, et al.
Published: (2025)

HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
by: Qiu, Pengyu, et al.
Published: (2022)