提出混合安全框架HySAFE-AI，提升大模型系统的安全评估能力。
HySafe-AI: Hybrid Safety Architectural Analysis Framework for AI Systems: A Case Study
- 融合传统方法与AI特性，改进FMEA和FTA在大模型中的适用性。
- 揭示基础模型隐空间表征对安全分析的关键影响。
- 适合关注自动驾驶与机器人安全的开发者与标准制定者。
人工智能已深度融入自动驾驶系统（ADS）与机器人等关键安全领域。当前自主系统架构正趋向于端到端（E2E）的单体化设计，如大型语言模型（LLMs）与视觉语言模型（VLMs）。本文综述了不同架构方案，并评估了常见安全分析方法——故障模式与影响分析（FMEA）与故障树分析（FTA）的有效性。研究发现，这些方法需针对基础模型的复杂性进行改进，尤其是在其形成与利用隐空间表征方面。为此，本文提出HySAFE-AI：一种面向人工智能系统的混合安全架构分析框架，通过适配传统方法来提升对AI系统安全性的评估能力。最后，文章给出未来研究方向与推动人工智能安全标准演进的建议。
原文摘要 · Abstract (English)
AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models (LLMs) and vision language models (VLMs). In this paper, we review different architectural solutions and then evaluate the efficacy of common safety analyses such as failure modes and effect analysis (FMEA) and fault tree analysis (FTA). We show how these techniques can be improved for the intricate nature of the foundational models, particularly in how they form and utilize latent representations. We introduce HySAFE-AI, Hybrid Safety Architectural Analysis Framework for AI Systems, a hybrid framework that adapts traditional methods to evaluate the safety of AI systems. Lastly, we offer hints of future work and suggestions to guide the evolution of future AI safety standards.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。