MR-052 Model & system behaviour System scope

Emergent dangerous capabilities

The system exhibits emergent dangerous capabilities such as deception, power-seeking, self-proliferation, situational awareness, or scheming, which a deployer must detect and contain.

Risk family: Model & system behaviour
MIT domain: 7. AI System Safety, Failures, & Limitations
MIT subdomain: 7.2 > AI possessing dangerous capabilities
AI type: GPAI, Agentic
Scope: System
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

MIT source entries

49 entries across 19 papers

Anwar2024Foundational Challenges in Assuring Alignment and Safety of Large Language Models73.01.03 73.01.05
Ferrara2023GenAI against humanity: nefarious applications of generative artificial intelligence and large language models46.04.01
G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.02.15
Gabriel2024The Ethics of Advanced AI Assistants24.02.04
Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.15.04 62.23.00 62.23.03 62.23.04 62.24.00 62.24.02
Hagendorff2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Review05.09.00
Hammond2025Multi-Agent Risks from Advanced AI63.04.03
Hendrycks2022X-Risk Analysis for AI Research35.06.00 35.08.00
InfoComm2023Cataloguing LLM Evaluations43.02.03 43.02.04 43.02.07 43.02.09 43.02.10
Ji2023AI Alignment: A Comprehensive Survey34.01.00 34.02.01 34.02.02 34.03.01
Leech2024Ten Hard Problems in Artificial Intelligence We Must Get Right54.03.02 54.03.03
Maas2023Advancing AI Governance: A Literature Review of Problems, Options, and Proposals53.02.00 53.02.01 53.02.03 53.02.04 53.02.05 53.02.06 53.02.07
McLean2023The risks associated with Artificial General Intelligence: A systematic review08.02.00
Meek2016Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review09.04.02
Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.18.00
Shevlane2023Model Evaluation for Extreme Risks25.06.00 25.07.00 25.08.00
Tan2022The Risks of Machine Learning Systems15.01.09
Tse2025Frontier AI Risk Management Framework (v1.0)72.05.02 72.05.03 72.05.05 72.05.06 72.06.03 72.06.04 72.06.06
Uuk2025A Taxonomy of Systemic Risks from General-Purpose AI61.02.18 61.02.36

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.11, A.10; src 7; mech B.8 | 42001 ctrl A.6.2.4

GPAI Code of Practice

S&S Ch. Commitments 2-5

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

A.10 ISO/IEC 23894 Annex A A.10
A.11 ISO/IEC 23894 Annex A A.11

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

CoP S&S Ch. Commitments 2-5

More in Model & system behaviour

MR-001 MR-002 MR-003 MR-004 MR-005 MR-006 MR-007 MR-008 MR-019 MR-021 MR-022 MR-023 MR-025 MR-026 MR-027 MR-028 MR-029 MR-031 MR-049 MR-050 MR-051 MR-053 MR-055 MR-056 MR-057 MR-058 MR-059 MR-061

See all Model & system behaviour risks →

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.