一句话：首次系统梳理大语言模型供应链各组件及其集成中的安全风险，总结出12类风险并给出构建更安全LLM系统的指引。
大语言模型正在改变软件开发范式，并被广泛用于构建各类应用。现有工作多从模型层面保障LLM质量与安全，缺乏对整个LLM系统构建过程（即LLM供应链）的全面理解，尤其对其中隐藏的安全问题探索不足。本文迈出第一步，讨论LLM供应链中每个组件以及组件集成之间可能存在的安全风险，总结出12类安全相关风险，并为构建更安全的LLM系统提供方向性建议。作者希望该工作能推动安全LLM生态下通用人工智能的演进。
Large Language Model (LLM) is changing the software development paradigm and has gained huge attention from both academia and industry. Researchers and developers collaboratively explore how to leverage the powerful problem-solving ability of LLMs for specific domain tasks. Due to the wide usage of LLM-based applications, e.g., ChatGPT, multiple works have been proposed to ensure the security of LLM systems. A comprehensive understanding of the entire process of LLM system construction (the LLM supply chain) is crucial, but relevant works are limited. More importantly, the security issues hidden in the LLM SC that could greatly impact the reliable usage of LLMs lack exploration. Most existing works mainly focus on assuring the quality of LLM from the model level; however, security assurance for the entire LLM SC is ignored. In this work, we take the first step to discuss the potential security risks in each component and the integration between components of LLM SC. We summarize 12 security-related risks and provide promising guidance to help build safer LLM systems. We hope our work can facilitate the evolution of artificial general intelligence with secure LLM ecosystems.
DOI 原文 ·
@inproceedings{paperbot9607,
title = {Large Language Model Supply Chain: Open Problems From the Security Perspective},
author = {Qiang Hu and Xiaofei Xie and Sen Chen and Lili Quan and Lei Ma},
booktitle = {ISSTA},
year = {2025},
doi = {10.1145/3713081.3731747}
}