paper-with-me

Papers

From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging

2026-06-10 · Zhenqian Zhu, Yamin Hu, Yiya Diao, Weixiang Li, Haodong Li, Wenjian Luo arxiv

Model merging (MM) has gained significant attention as a cost-effective approach to integrate multiple task-specific models into a unified model. However, recent work reveals that MM is highly susceptible to backdoor attacks. Existing defenses based on task arithmetic often fail to eliminate backdoors without substantially degrading clean-task performance, owing to their reliance on direct parameter-space editing. To address this gap, we propose Linear Feature Path Minimization (LFPM), a backdoor mitigation framework for model merging, which introduces an anti-backdoor task vector into the backdoored merged model. Unlike prior approaches, LFPM formulates the backdoor robustness of the merged model from a unified feature-space perspective under the Cross-Task Linearity (CTL) framework, which leverages the approximate linearity of features across tasks. This perspective guides the optimization of the anti-backdoor task to suppress backdoors while preserving clean-task performance. Furthermore, we introduce an effective optimization mechanism based on gradient accumulation and loss path-integral, ensuring robust backdoor suppression along the interpolation path. Extensive experiments demonstrate that LFPM consistently exhibits strong robustness against backdoor attacks in both full fine-tuning and Parameter-Efficient Fine-Tuning (PEFT) settings.

📄 PDF Abstract BibTeX arXiv:2606.12498

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors

2025-01-04 · Chia-Yi Hsu, Yu-Lin Tsai, Yu Zhe, Yan-Lun Chen 외

Task arithmetic in large-scale pre-trained models enables agile adaptation to diverse downstream tasks without extensive retraining. By leveraging task vectors (TVs), users can perform modular updates through simple arit…

Backdoor AttackTask Arithmetic

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

2024-01-20 · Zhen Xiang, Fengqing Jiang, Zidi Xiong, Bhaskar Ramasubramanian 외

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulne…

Backdoor Attack

Towards Backdoor Stealthiness in Model Parameter Space

2025-01-10 · Xiaoyun Xu, Zhuoran Liu, Stefanos Koffas, Stjepan Picek

Recent research on backdoor stealthiness focuses mainly on indistinguishable triggers in input space and inseparable backdoor representations in feature space, aiming to circumvent backdoor defenses that examine these re…

backdoor defensemodel

Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses

2025-10-09 · Stanisław Pawlak, Jan Dubiński, Daniel Marczak, Bartłomiej Twardowski arxiv

Model merging (MM) recently emerged as an effective method for combining large deep learning models. However, it poses significant security risks. Recent research shows that it is highly susceptible to backdoor attacks, …

Neighboring Backdoor Attacks on Graph Convolutional Network

2022-01-17 · Liang Chen, Qibiao Peng, Jintang Li, Yang Liu 외

Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their succ…

Backdoor Attack