DARR
MR-030 Human & usage System scope

Manipulation, persuasion and dark patterns

The system covertly manipulates user beliefs or behavior through persuasion, nudging, dark patterns, or exploitation of cognitive biases.

Risk family
Human & usage
MIT domain
7. AI System Safety, Failures, & Limitations
MIT subdomain
5.1 > Overreliance and unsafe use
AI type
GPAI, Agentic
Scope
System
Source standard
MIT AI Risk Repository v4

Provenance

Source standard
MIT AI Risk Repository v4
MIT source entries
33 entries across 22 papers
  • Abercrombie2024A Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation Harms58.03.04 58.03.08
  • Allianz2018The Rise of Artificial Intelligence - Future Outlooks and Emerging Risks41.04.00 41.04.02
  • Clarke2023A Survey of the Potential Long-term Impacts of AI: How AI Could Lead to Long-term Changes in Science, Cooperation, Power, Epistemics and Values55.04.03
  • Cui2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems02.06.02
  • DSIT2023Capabilities and Risks from Frontier AI67.04.04
  • G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.02.01
  • Gabriel2024The Ethics of Advanced AI Assistants24.04.00 24.05.02 24.06.03
  • Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.19.12 62.21.00 62.24.01 62.25.00 62.26.00
  • GOS2023Future Risks of Frontier AI56.04.00 56.05.00
  • Hagendorff2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Review05.06.00
  • Hogenhout2021A framework for ethical Ai at the United Nations06.09.00
  • InfoComm2023Cataloguing LLM Evaluations43.02.05
  • Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.07.04
  • Meek2016Managing the ethical and risk implications of rapid advances in artificial intelligence: A literature review09.02.07
  • NIST2024Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile48.03.00
  • Shelby2023Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction11.04.03 11.05.03
  • Shevlane2023Model Evaluation for Extreme Risks25.03.00
  • Tan2022The Risks of Machine Learning Systems15.02.07
  • Tse2025Frontier AI Risk Management Framework (v1.0)72.05.09
  • Uuk2025A Taxonomy of Systemic Risks from General-Purpose AI61.02.49
  • Weidinger2022Taxonomy of Risks posed by Language Models16.05.03 16.05.04
  • Weidinger2023Sociotechnical Safety Evaluation of Generative AI Systems18.05.02

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.5.4, A.9.4
EU AI Act articles
Art. 5(a) | Art. 5(b)

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.9.4 ISO/IEC 42001 Annex A A.9.4
2
  • Art. 5(a)
  • Art. 5(b)
Cross-checksframeworks mapped in to test coverage
1
  • ASI09 Human-Agent Trust Exploitation

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.