# Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks

arXiv: https://arxiv.org/abs/2508.06411 · HTML: https://mlsanity.com/paper/2508.06411/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 63 of its 140 references that are in the map.
- First posted on arXiv 8 Aug 2025.

## Builds on (most cited first, 30 of 63)

- [An Overview of Catastrophic AI Risks](https://mlsanity.com/paper/2306.12001/) (2023)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation](https://mlsanity.com/paper/1802.07228/) (2018)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Teams of LLM Agents can Exploit Zero-Day Vulnerabilities](https://mlsanity.com/paper/2406.01637/) (2024)
- [Visibility into AI Agents](https://mlsanity.com/paper/2401.13138/) (2024)
- [Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?](https://mlsanity.com/paper/2502.15657/) (2025)
- [Artificial Intelligence Index Report 2025](https://mlsanity.com/paper/2504.07139/) (2025)
- [Open Problems in Technical AI Governance](https://mlsanity.com/paper/2407.14981/) (2024)
- [Gradual Disempowerment: Systemic Existential Risks from Incremental AI Development](https://mlsanity.com/paper/2501.16946/) (2025)
- [Artificial intelligence and biological misuse: Differentiating risks of language models and biological design tools](https://mlsanity.com/paper/2306.13952/) (2023)
- [An Approach to Technical AGI Safety and Security](https://mlsanity.com/paper/2504.01849/) (2025)
- [Infrastructure for AI Agents](https://mlsanity.com/paper/2501.10114/) (2025)
- [AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies](https://mlsanity.com/paper/2406.17864/) (2024)
- [Towards evaluations-based safety cases for AI scheming](https://mlsanity.com/paper/2411.03336/) (2024)
- [Ecosystem Graphs: The Social Footprint of Foundation Models](https://mlsanity.com/paper/2303.15772/) (2023)
- [TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI](https://mlsanity.com/paper/2306.06924/) (2023)
- [Two Types of AI Existential Risk: Decisive and Accumulative](https://mlsanity.com/paper/2401.07836/) (2024)
- [Risk assessment at AGI companies: A review of popular risk assessment techniques from other safety-critical industries](https://mlsanity.com/paper/2307.08823/) (2023)
- [A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms](https://mlsanity.com/paper/2407.01294/) (2024)
- [Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects](https://mlsanity.com/paper/2505.18893/) (2025)
- [Towards more Practical Threat Models in Artificial Intelligence Security](https://mlsanity.com/paper/2311.09994/) (2023)
- [Current and Near-Term AI as a Potential Existential Risk Factor](https://mlsanity.com/paper/2209.10604/) (2022)
- [A Taxonomy of Systemic Risks from General-Purpose AI](https://mlsanity.com/paper/2412.07780/) (2024)
- [Societal Adaptation to Advanced AI](https://mlsanity.com/paper/2405.10295/) (2024)
- [Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures](https://mlsanity.com/paper/1610.07997/) (2016)
- [A taxonomic system for failure cause analysis of open source AI incidents](https://mlsanity.com/paper/2211.07280/) (2022)
- [The Reality of AI and Biorisk](https://mlsanity.com/paper/2412.01946/) (2024)

## Built on by (most cited first, 1 of 1)

- [Reframing AI Loss of Control: What Control Is, How to Have It, How to Lose It](https://mlsanity.com/paper/2606.12442/) (2026)

## Abstract (arXiv)

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.