DARR
MR-049 Model & system behaviour System scope

Physical safety harm and accidents

Failures of AI in safety-critical systems, critical infrastructure, or embodied/robotic settings cause physical injury, accidents, or property damage.

Risk family
Model & system behaviour
MIT domain
7. AI System Safety, Failures, & Limitations
MIT subdomain
X.1 > Excluded
AI type
GPAI, Agentic, Classical_ML
Scope
System
Source standard
MIT AI Risk Repository v4

Provenance

Source standard
MIT AI Risk Repository v4
MIT source entries
49 entries across 25 papers
  • Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.02.00 58.02.01 58.02.03 58.02.04 58.07.05 58.08.01
  • AIVerify2023Summary Report: Binary Classification Model for Credit Risk26.04.00
  • Allianz2018The Rise of Artificial Intelligence - Future Outlooks and Emerging Risks41.03.00 41.03.02
  • Cunha2023Navigating the Landscape of AI Ethics and Responsibility03.01.00
  • Everitt2018AGI Safety Literature Review51.05.00 51.10.00
  • Gabriel2024The Ethics of Advanced AI Assistants24.01.00 24.01.01 24.10.04
  • Ghosh2024AILUMINATE: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons57.01.00 57.02.05
  • Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.07.03 62.07.04 62.30.01 62.30.03
  • Hendrycks2023An Overview of Catastrophic AI Risks22.03.00 22.03.01 22.03.02
  • Kilian2023Examining the differential risk from high-level artificial intelligence and the question of control07.02.00
  • Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.11.00 66.11.02 66.11.04 66.11.05
  • Maham2023Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks52.01.03
  • Meek2016Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review09.05.01 09.05.02
  • Paes2023Social Impacts of Artificial Intelligence and Mitigation Recommendations: An Exploratory Study10.02.00
  • Perlo2025Embodied AI: Emerging Risks and Opportunities for Policy Action70.01.00 70.01.02
  • Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.10.00
  • Schnitzer2024AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks59.01.00
  • Steimers2022Sources of Risk of AI Systems14.06.00
  • Tan2022The Risks of Machine Learning Systems15.02.01
  • Tang2025Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy71.01.04 71.03.02
  • Teixeira2022An Exploratory Diagnosis of Artificial Intelligence Risks for a Responsible Governance42.04.00 42.23.00
  • Tse2025Frontier AI Risk Management Framework (v1.0)72.01.03 72.03.00 72.03.01
  • Weidinger2021Ethical and social risks of harm from language models17.06.04
  • Weidinger2022Taxonomy of Risks posed by Language Models16.06.04
  • Weidinger2023Sociotechnical Safety Evaluation of Generative AI Systems18.06.01

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 5, 8; mech B.2 | 42001 ctrl A.5.4, A.6.2.4

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.5.4 ISO/IEC 42001 Annex A A.5.4
  • A.6.2.4 ISO/IEC 42001 Annex A A.6.2.4

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.