DARR
MR-029 Model & system behaviour System scope

Facilitation of weapons, CBRN and serious physical harm (capability uplift)

The system lowers barriers to chemical, biological, radiological, nuclear, explosive or other weapons and dangerous activities by providing actionable how-to information or uplift.

Risk family
Model & system behaviour
MIT domain
4. Malicious Actors & Misuse
MIT subdomain
4.2 > Cyberattacks, weapon development or use, and mass harm
AI type
GPAI, Agentic
Scope
System
Source standard
MIT AI Risk Repository v4

Provenance

Source standard
MIT AI Risk Repository v4
MIT source entries
41 entries across 23 papers
  • Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.07.15
  • Anwar2024Foundational Challenges in Assuring Alignment and Safety of Large Language Models73.03.05
  • Bengio2025International AI Safety Report 202560.01.04
  • Chin2025Dimensional Characterization and Pathway Modeling for Catastrophic AI Risks68.01.00
  • Clarke2023A Survey of the Potential Long-term Impacts of AI: How AI Could Lead to Long-term Changes in Science, Cooperation, Power, Epistemics and Values55.02.01
  • DSIT2023Capabilities and Risks from Frontier AI67.03.00 67.03.01
  • G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.02.03
  • Gabriel2024The Ethics of Advanced AI Assistants24.03.06
  • Ghosh2024AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons57.01.04
  • Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.05.00 62.08.06 62.29.02 62.33.01 62.33.02
  • Hendrycks2022X-Risk Analysis for AI Research35.01.00
  • Hendrycks2023An Overview of Catastrophic AI Risks22.01.01
  • InfoComm2023Cataloguing LLM Evaluations43.02.02 43.02.06
  • Maas2023Advancing AI Governance: A Literature Review of Problems, Options, and Proposals53.03.06
  • Maham2023Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks52.02.00 52.02.02
  • NIST2024Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile48.01.00
  • Shevlane2023Model Evaluation for Extreme Risks25.05.00
  • Tang2025Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy71.01.01 71.01.02 71.01.03
  • TC2602024AI Safety Governance Framework45.02.08
  • Tse2025Frontier AI Risk Management Framework (v1.0)72.01.02 72.05.11
  • Uuk2025A Taxonomy of Systemic Risks from General-Purpose AI61.01.13 61.02.02
  • Vidgen2024Introducing v0.5 of the AI Safety Benchmark from MLCommons23.02.06 23.05.00 23.05.01 23.05.02 23.05.03 23.05.04 23.05.05 23.05.06
  • Weidinger2023Sociotechnical Safety Evaluation of Generative AI Systems18.04.04

Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.

ISO/IEC references
23894 obj A.10; src 7 | 42001 ctrl A.5.5, A.9.4

Framework crosswalk

Every framework item mapped to this risk. Items marked partial overlap only in part; definitions appear on hover where the source licence permits.

Sourcesframeworks that contributed to the register
1
  • A.10 ISO/IEC 23894 Annex A A.10
2
  • A.5.5 ISO/IEC 42001 Annex A A.5.5
  • A.9.4 ISO/IEC 42001 Annex A A.9.4
Cross-checksframeworks mapped in to test coverage
1
  • AISubtech-15.1.18 Safety Harms and Toxicity: Weapons / CBRN Risks
1
  • GENAI.1 CBRN Information or Capabilities

Part of the Deployer AI Risk Register, an open-source resource powered by MindXO. Version 1.0, 3 July 2026. Derived from the MIT AI Risk Repository (V4, December 2025) under CC BY 4.0; an independent derivative work, not endorsed by or affiliated with MIT. Sub-risk decomposition references MITRE ATLAS™ v5.6.0 (© 2021-2026 The MITRE Corporation, reproduced and distributed with permission). ISO/IEC and EU AI Act references are by number only. License: CC BY 4.0. Full attribution and licensing.