New framework quantifies AI harms in critical infrastructure systems

A new research paper proposes a framework to quantify the system-level harms that can arise from integrating AI into complex sociotechnical systems, such as Critical National Infrastructure. The proposed method connects structured hazard analysis, component-level testing, and probabilistic system modeling to assess the impact of AI failures on overall system risk. An application to the UK's Real Time Gross Settlement system demonstrated how adversarial manipulation of AI trading recommendations could lead to increased bank failures and financial contagion. AI

影响 Provides a method to assess the systemic risks of AI in critical infrastructure, enabling better governance and mitigation strategies.

排序理由 The cluster contains an academic paper detailing a new framework for AI safety research. [lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

• Critical National Infrastructure
• Paul Vautravers
• real-time gross settlement
• Systems Theoretic Process Analysis for Layers of System Safety
• UK

• 论文
• 安全
• 政策

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →