arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2411.01604cs.CRcs.AIcs.SE
收藏

大型语言模型供应链:从安全视角看开放问题

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

The University of Tokyo(东京大学);Singapore Management University(新加坡管理大学);Tianjin University(天津大学);University of Alberta(阿尔伯塔大学)

Qiang Hu, Xiaofei Xie, Sen Chen, Lei Ma

AI总结:

本文从安全视角系统审视大型语言模型供应链,识别各组件及集成中的12项安全风险,并提出构建更安全LLM系统的指导性建议。

摘要:

大型语言模型(LLM)正在改变软件开发范式,并已引起学术界和工业界的广泛关注。研究人员和开发者合作探索如何利用LLM强大的问题解决能力来处理特定领域任务。由于基于LLM的应用(如ChatGPT)被广泛使用,已有多个工作致力于确保LLM系统的安全性。然而,全面理解LLM系统构建的整个过程(即LLM供应链)至关重要,但相关研究却十分有限。更重要的是,隐藏在LLM供应链中可能严重影响LLM可靠使用的安全问题缺乏探索。现有工作主要侧重于从模型层面保证LLM的质量,而忽视了整个LLM供应链的安全保障。在本工作中,我们迈出第一步,讨论LLM供应链中每个组件以及组件之间集成所存在的潜在安全风险。我们总结了12项与安全相关的风险,并提供了有前景的指导,以帮助构建更安全的LLM系统。我们希望我们的工作能够通过安全的LLM生态系统促进通用人工智能的发展。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑