A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908346179649536 |
|---|---|
| author | Ding, Ziqi Fu, Qian Ding, Junchen Deng, Gelei Liu, Yi Li, Yuekang |
| author_facet | Ding, Ziqi Fu, Qian Ding, Junchen Deng, Gelei Liu, Yi Li, Yuekang |
| contents | Recent advancements in large language models (LLMs) have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI supply chains such as Hugging Face, which host pretrained models and their associated configuration files contributed by the public, face significant security challenges; in particular, configuration files originally intended to set up models by specifying parameters and initial settings can be exploited to execute unauthorized code, yet research has largely overlooked their security compared to that of the models themselves; in this work, we present the first comprehensive study of malicious configurations on Hugging Face, identifying three attack scenarios (file, website, and repository operations) that expose inherent risks; to address these threats, we introduce CONFIGSCAN, an LLM-based tool that analyzes configuration files in the context of their associated runtime code and critical libraries, effectively detecting suspicious elements with low false positive rates and high accuracy; our extensive evaluation uncovers thousands of suspicious repositories and configuration files, underscoring the urgent need for enhanced security validation in AI model hosting platforms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01067 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories Ding, Ziqi Fu, Qian Ding, Junchen Deng, Gelei Liu, Yi Li, Yuekang Cryptography and Security Artificial Intelligence Recent advancements in large language models (LLMs) have spurred the development of diverse AI applications from code generation and video editing to text generation; however, AI supply chains such as Hugging Face, which host pretrained models and their associated configuration files contributed by the public, face significant security challenges; in particular, configuration files originally intended to set up models by specifying parameters and initial settings can be exploited to execute unauthorized code, yet research has largely overlooked their security compared to that of the models themselves; in this work, we present the first comprehensive study of malicious configurations on Hugging Face, identifying three attack scenarios (file, website, and repository operations) that expose inherent risks; to address these threats, we introduce CONFIGSCAN, an LLM-based tool that analyzes configuration files in the context of their associated runtime code and critical libraries, effectively detecting suspicious elements with low false positive rates and high accuracy; our extensive evaluation uncovers thousands of suspicious repositories and configuration files, underscoring the urgent need for enhanced security validation in AI model hosting platforms. |
| title | A Rusty Link in the AI Supply Chain: Detecting Evil Configurations in Model Repositories |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2505.01067 |