一句话：通过分析 Hugging Face 与 GitHub 讨论，构建 AI 项目安全问题与解决方案分类体系，揭示 AI 供应链安全挑战。
AI 模型与应用快速增长带来复杂安全态势。AI 项目开发者既要应对传统软件供应链问题，也要面对 AI 特有安全威胁，但实践中常见哪些安全问题及如何解决仍缺乏了解。该文基于 Hugging Face 和 GitHub 的开发者讨论开展实证研究：先构建关键词匹配与最优微调 distilBERT 分类器结合的流水线，从多种深度学习与大语言模型比较中选出最佳分类器，得到 312,868 条安全讨论；再从中抽样 753 条帖子进行主题分析，归纳出覆盖（1）系统与软件、（2）外部工具与生态、（3）模型、（4）数据四个主题的细粒度分类体系，包含 32 类安全问题和 24 类解决方案。研究发现许多安全问题源于 AI 组件的复杂依赖与黑箱特性，且模型与数据相关挑战常缺乏具体解决方案。该结果为 AI 供应链各环节的安全实践提供证据。
The rapid growth of Artificial Intelligence (AI) models and applications has led to an increasingly complex security landscape. Developers of AI projects must contend not only with traditional software supply chain issues but also with novel, AI-specific security threats. However, little is known about what security issues are commonly encountered and how they are resolved in practice. This gap hinders the development of effective security measures for each component of the AI supply chain. We bridge this gap by conducting an empirical investigation of developer-reported issues and solutions, based on discussions from Hugging Face and GitHub. To identify security-related discussions, we develop a pipeline that combines keyword matching with an optimal fine-tuned distilBERT classifier, which achieved the best performance in our extensive comparison of various deep learning and large language models. This pipeline produces a dataset of 312,868 security discussions, providing insights into the security reporting practices of AI applications and projects. We conduct a thematic analysis of 753 posts sampled from our dataset and uncover a fine-grained taxonomy of 32 security issues and 24 solutions across four themes: (1) System and Software, (2) External Tools and Ecosystem, (3) Model, and (4) Data. We reveal that many security issues arise from the complex dependencies and black-box nature of AI components. Notably, challenges related to Models and Data often lack concrete solutions. Our insights can offer evidence-based guidance for developers and researchers to address real-world security threats across the AI supply chain.
@inproceedings{abs-2512-23385,
title = {Securing the AI Supply Chain: What Can We Learn From Developer-Reported Security Issues and Solutions of AI Projects?},
author = {The Anh Nguyen and Triet Huynh Minh Le and M. Ali Babar},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787796}
}