Saved in:
Bibliographic Details
Main Authors: Lyu, Liangwei, Xu, Jiaqi, Ding, Jianwei, Deng, Qiyao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.21977
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915954053611520
author Lyu, Liangwei
Xu, Jiaqi
Ding, Jianwei
Deng, Qiyao
author_facet Lyu, Liangwei
Xu, Jiaqi
Ding, Jianwei
Deng, Qiyao
contents Low-Rank Adaptation (LoRA) has emerged as a leading technique for efficiently fine-tuning text-to-image diffusion models, and its widespread adoption on open-source platforms has fostered a vibrant culture of model sharing and customization. However, the same modular and plug-and-play flexibility that makes LoRA appealing also introduces a broader attack surface. To highlight this risk, we propose Masquerade-LoRA (MasqLoRA), the first systematic attack framework that leverages an independent LoRA module as the attack vehicle to stealthily inject malicious behavior into text-to-image diffusion models. MasqLoRA operates by freezing the base model parameters and updating only the low-rank adapter weights using a small number of "trigger word-target image" pairs. This enables the attacker to train a standalone backdoor LoRA module that embeds a hidden cross-modal mapping: when the module is loaded and a specific textual trigger is provided, the model produces a predefined visual output; otherwise, it behaves indistinguishably from the benign model, ensuring the stealthiness of the attack. Experimental results demonstrate that MasqLoRA can be trained with minimal resource overhead and achieves a high attack success rate of 99.8%. MasqLoRA reveals a severe and unique threat in the AI supply chain, underscoring the urgent need for dedicated defense mechanisms for the LoRA-centric sharing ecosystem.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21977
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters
Lyu, Liangwei
Xu, Jiaqi
Ding, Jianwei
Deng, Qiyao
Computer Vision and Pattern Recognition
Low-Rank Adaptation (LoRA) has emerged as a leading technique for efficiently fine-tuning text-to-image diffusion models, and its widespread adoption on open-source platforms has fostered a vibrant culture of model sharing and customization. However, the same modular and plug-and-play flexibility that makes LoRA appealing also introduces a broader attack surface. To highlight this risk, we propose Masquerade-LoRA (MasqLoRA), the first systematic attack framework that leverages an independent LoRA module as the attack vehicle to stealthily inject malicious behavior into text-to-image diffusion models. MasqLoRA operates by freezing the base model parameters and updating only the low-rank adapter weights using a small number of "trigger word-target image" pairs. This enables the attacker to train a standalone backdoor LoRA module that embeds a hidden cross-modal mapping: when the module is loaded and a specific textual trigger is provided, the model produces a predefined visual output; otherwise, it behaves indistinguishably from the benign model, ensuring the stealthiness of the attack. Experimental results demonstrate that MasqLoRA can be trained with minimal resource overhead and achieves a high attack success rate of 99.8%. MasqLoRA reveals a severe and unique threat in the AI supply chain, underscoring the urgent need for dedicated defense mechanisms for the LoRA-centric sharing ecosystem.
title When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign Adapters
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.21977