Large Language Model Supply Chain: Open Problems From the Security Perspective

TL;DR

This paper explores security challenges across the entire Large Language Model supply chain, identifying risks and providing guidance to develop safer LLM systems amidst growing reliance on these models.

Contribution

It offers the first comprehensive analysis of security issues in the LLM supply chain, highlighting risks at each component and their integration, which was previously underexplored.

Findings

Identified 12 security-related risks in LLM supply chain

Provided guidance for building safer LLM systems

Highlighted the importance of security in LLM ecosystem evolution

Abstract

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. However, a comprehensive understanding of the entire processes 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 which could highly impact the reliable usage of LLMs are lack of exploration. Existing works mainly focus on assuring the quality of LLM from the model level, 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 as well as 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.