Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks
This work addresses the problem of unstructured risk discourse for AI safety researchers and policymakers, offering a systematic approach to identify and mitigate catastrophic risks, though it is incremental in building on existing risk discussions.
The paper tackles the lack of a comprehensive framework for AI catastrophic risks by characterizing six risks across seven dimensions and modeling causal pathways from hazard to harm, aiming to provide a structured foundation for risk management.
Although discourse around the risks of Artificial Intelligence (AI) has grown, it often lacks a comprehensive, multidimensional framework, and concrete causal pathways mapping hazard to harm. This paper aims to bridge this gap by examining six commonly discussed AI catastrophic risks: CBRN, cyber offense, sudden loss of control, gradual loss of control, environmental risk, and geopolitical risk. First, we characterize these risks across seven key dimensions, namely intent, competency, entity, polarity, linearity, reach, and order. Next, we conduct risk pathway modeling by mapping step-by-step progressions from the initial hazard to the resulting harms. The dimensional approach supports systematic risk identification and generalizable mitigation strategies, while risk pathway models help identify scenario-specific interventions. Together, these methods offer a more structured and actionable foundation for managing catastrophic AI risks across the value chain.