paper-with-me

Papers

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem

2024-02-29 · Hongyi Liu, Shaochen Zhong, Xintong Sun, Minghao Tian, Mohsen Hariri, Zirui Liu, Ruixiang Tang, Zhimeng Jiang, Jiayi Yuan, Yu-Neng Chuang, Li Li, Soo-Hyun Choi, Rui Chen, Vipin Chaudhary, Xia Hu

Finetuning LLMs with LoRA has gained significant popularity due to its simplicity and effectiveness. Often, users may even find pluggable, community-shared LoRAs to enhance their base models for a specific downstream task of interest; enjoying a powerful, efficient, yet customized LLM experience with negligible investment. However, this convenient share-and-play ecosystem also introduces a new attack surface, where attackers can distribute malicious LoRAs to a community eager to try out shared assets. Despite the high-risk potential, no prior art has comprehensively explored LoRA's attack surface under the downstream-enhancing share-and-play context. In this paper, we investigate how backdoors can be injected into task-enhancing LoRAs and examine the mechanisms of such infections. We find that with a simple, efficient, yet specific recipe, a backdoor LoRA can be trained once and then seamlessly merged (in a training-free fashion) with multiple task-enhancing LoRAs, retaining both its malicious backdoor and benign downstream capabilities. This allows attackers to scale the distribution of compromised LoRAs with minimal effort by leveraging the rich pool of existing shared LoRA assets. We note that such merged LoRAs are particularly infectious -- because their malicious intent is cleverly concealed behind improved downstream capabilities, creating a strong incentive for voluntary download -- and dangerous -- because under local deployment, no safety measures exist to intervene when things go wrong. Our work is among the first to study this new threat model of training-free distribution of downstream-capable-yet-backdoor-injected LoRAs, highlighting the urgent need for heightened security awareness in the LoRA ecosystem. Warning: This paper contains offensive content and involves a real-life tragedy.

📄 PDF Abstract BibTeX arXiv:2403.00108

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Shortcuts Everywhere and Nowhere: Exploring Multi-Trigger Backdoor Attacks

2024-01-27 · Yige Li, Jiabo He, Hanxun Huang, Jun Sun 외

Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely o…

Weight space Detection of Backdoors in LoRA Adapters

2026-02-16 · David Puertolas Merenciano, Ekaterina Vasyagina, Kevin Zhu, Javier Ferrando 외 arxiv

LoRA adapters let users fine-tune large language models (LLMs) efficiently. However, LoRA adapters are shared through open repositories like Hugging Face Hub \citep{huggingface_hub_docs}, making them vulnerable to backdo…

Shared Latent Structures Enable Unified Backdoor Detection and Mitigation in LLMs

2026-06-06 · Omar Mahmoud, Aly M. Kassem, Thommen George Karimpanal, Buddhika Laknath Semage 외 arxiv

Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors. We show this view is incomplete. Across diverse ba…

Char-mander Use mBackdoor! A Study of Cross-lingual Backdoor Attacks in Multilingual LLMs

2025-02-24 · Himanshu Beniwal, Sailesh Panda, Birudugadda Srivibhav, Mayank Singh

We explore \textbf{C}ross-lingual \textbf{B}ackdoor \textbf{AT}tacks (X-BAT) in multilingual Large Language Models (mLLMs), revealing how backdoors inserted in one language can automatically transfer to others through sh…

Cross-Lingual Transfer

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space

2024-02-19 · Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning wh…