Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dong, Yueyan, Xu, Minghui, Hu, Qin, Xiao, Yinhao, Luo, Qi, Zhang, Yechao, Zhang, Yue, Cheng, Xiuzhen
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909979923972096
author Dong, Yueyan
Xu, Minghui
Hu, Qin
Xiao, Yinhao
Luo, Qi
Zhang, Yechao
Zhang, Yue
Cheng, Xiuzhen
author_facet Dong, Yueyan
Xu, Minghui
Hu, Qin
Xiao, Yinhao
Luo, Qi
Zhang, Yechao
Zhang, Yue
Cheng, Xiuzhen
contents Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing trainable low-rank matrices. However, when integrated with frameworks like FedIT, LoRA introduces a critical vulnerability: clients submit $A$ and $B$ matrices separately, while only their product $AB$ determines the model update, yet this composite is never directly verified. We propose Gradient Assembly Poisoning (GAP), a novel attack that exploits this blind spot by crafting individually benign $A$ and $B$ matrices whose product yields malicious updates. GAP operates without access to training data or inter-client coordination and remains undetected by standard anomaly detectors. We identify four systemic vulnerabilities in LoRA-based federated systems and validate GAP across LLaMA, ChatGLM, and GPT-2. GAP consistently induces degraded or biased outputs while preserving surface fluency, reducing BLEU by up to 14.5\%, increasing factual and grammatical errors by over 800\%, and maintaining 92.6\% long-form response length. These results reveal a new class of stealthy, persistent threats in distributed LoRA fine-tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00566
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
Dong, Yueyan
Xu, Minghui
Hu, Qin
Xiao, Yinhao
Luo, Qi
Zhang, Yechao
Zhang, Yue
Cheng, Xiuzhen
Cryptography and Security
Low-Rank Adaptation (LoRA) has become a popular solution for fine-tuning large language models (LLMs) in federated settings, dramatically reducing update costs by introducing trainable low-rank matrices. However, when integrated with frameworks like FedIT, LoRA introduces a critical vulnerability: clients submit $A$ and $B$ matrices separately, while only their product $AB$ determines the model update, yet this composite is never directly verified. We propose Gradient Assembly Poisoning (GAP), a novel attack that exploits this blind spot by crafting individually benign $A$ and $B$ matrices whose product yields malicious updates. GAP operates without access to training data or inter-client coordination and remains undetected by standard anomaly detectors. We identify four systemic vulnerabilities in LoRA-based federated systems and validate GAP across LLaMA, ChatGLM, and GPT-2. GAP consistently induces degraded or biased outputs while preserving surface fluency, reducing BLEU by up to 14.5\%, increasing factual and grammatical errors by over 800\%, and maintaining 92.6\% long-form response length. These results reveal a new class of stealthy, persistent threats in distributed LoRA fine-tuning.
title Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-based LLM Systems
topic Cryptography and Security
url https://arxiv.org/abs/2601.00566