DARR
MR-009 Data, privacy & content liability System scope

Leakage of personal or sensitive data

The system memorizes and discloses personal or sensitive data in its outputs, or such data is extracted via inference/extraction attacks, as distinct from the lawful basis for collecting or processing that data (MR-011).

Risk family
Data, privacy & content liability
MIT domain
2. Privacy & Security
MIT subdomain
2.1 > Compromise of privacy by leaking or correctly inferring sensitive information
AI type
GPAI, Classical_ML
Scope
System
Source standard
MIT AI Risk Repository v4

Provenance

Source standard
MIT AI Risk Repository v4
MIT source entries
66 entries across 34 papers
  • Bengio2024International Scientific Report on the Safety of Advanced AI49.03.05
  • Cui2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems02.01.03 02.07.00 02.07.01 02.07.02 02.07.03 02.09.04 02.10.02
  • Deng2023Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements04.06.00
  • G'sell2024Regulating under Uncertainty: Governance Options for Generative AI47.03.01 47.03.02 47.03.04
  • Gabriel2024The Ethics of Advanced AI Assistants24.05.01 24.08.00
  • Giarmoleo2024What Ethics Can Say on Artificial Intelligence: Insights from a Systematic Literature Review37.02.02
  • Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.16.08 62.28.00 62.38.01
  • Habbal2024Artificial Intelligence Trust, Risk and Security Management (AI TRiSM): Frameworks, Applications, Challenges and Future Research Directions29.01.02
  • Hagendorff2024Mapping the Ethics of Generative AI: A Comprehensive Scoping Review05.05.00 05.17.00
  • Hammond2025Multi-Agent Risks from Advanced AI63.10.04
  • Hogenhout2021A framework for ethical Ai at the United Nations06.02.00
  • IBM2025AI Risk Atlas65.03.01 65.03.03 65.11.01 65.11.02 65.16.02 65.20.01
  • InfoComm2023Cataloguing LLM Evaluations43.01.06
  • Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.09.03 66.09.07
  • Liu2024Trustworthy LLMs: A Survey and Guideline for Evaluating Large Language Models’ Alignment30.02.00 30.02.06 30.04.04
  • Maham2023Governing General Purpose AI: A Comprehensive Map of Unreliability, Misuse and Systemic Risks52.01.02
  • Marchal2024Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data64.05.01
  • NIST2024Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile48.04.00
  • Perlo2025Embodied AI: Emerging Risks and Opportunities for Policy Action70.02.01
  • Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.07.00
  • Schnitzer2024AI Hazard Management: A Framework for the Systematic Management of Root Causes for AI Risks59.10.00
  • Sherman2023AI Risk Profiles: A Standards Proposal for Pre-Deployment AI Risk Disclosures12.08.00
  • Stanley2024Emerging Risks and Mitigations for Public Chatbots: LILAC v169.05.00 69.05.01 69.05.02 69.09.03
  • Steimers2022Sources of Risk of AI Systems14.02.00
  • Tan2022The Risks of Machine Learning Systems15.02.04
  • TC2602024AI Safety Governance Framework45.01.10 45.02.01 45.02.03
  • Vidgen2024Introducing v0.5 of the AI Safety Benchmark from MLCommons23.09.00
  • Wang2025A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy74.01.00 74.01.01 74.01.04
  • Weidinger2021Ethical and social risks of harm from language models17.02.00 17.02.01 17.02.02
  • Weidinger2022Taxonomy of Risks posed by Language Models16.02.00 16.02.01 16.02.02
  • Weidinger2023Sociotechnical Safety Evaluation of Generative AI Systems18.03.01
  • Wirtz2022Governance of artificial intelligence: A risk and guideline-based integrative framework19.04.02
  • Zeng2024AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies50.04.04 50.04.05
  • Zhang2023SafetyBench: Evaluating the Safety of Large Language Models with Multiple Choice Questions28.07.00

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.8; src 6; mech B.5 | 42001 ctrl A.7.4, A.7.5, A.5.4

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.8 ISO/IEC 23894 Annex A A.8
3
  • A.5.4 ISO/IEC 42001 Annex A A.5.4
  • A.7.4 ISO/IEC 42001 Annex A A.7.4
  • A.7.5 ISO/IEC 42001 Annex A A.7.5
5

Expanded into this risk’s technique sub-risks.

Cross-checksframeworks mapped in to test coverage
2
  • ibm-exposing-personal-information Exposing personal information
  • ibm-sharing-ip-pi-confidential-information-with-user Sharing IP/PI/confidential information with user
3
  • AISubtech-15.1.25 Privacy Attacks: PII / PHI / PCI
  • AISubtech-8.2.1 Training Data Exposure
  • AISubtech-8.2.2 LLM Data Leakage
5
  • NISTAML.03 Privacy Compromises
  • NISTAML.032 Reconstruction partial
  • NISTAML.036 Leaking information from user interactions
  • NISTAML.037 Training Data Attacks
  • NISTAML.038 Data Extraction
1
  • GENAI.4 Data Privacy
2
  • LLM02:2025 Sensitive Information Disclosure
  • LLM08:2025 Vector and Embedding Weaknesses partial

Sub-risks (3)

Technique-level decompositions of this risk, each anchored to the MITRE ATLAS technique it derives from.

MR-009.1

Prompt-induced leakage of sensitive data

#

Crafted prompts induce the model to reveal sensitive data from its training set, context, or memory.

MITRE ATLAS technique: AML.T0057 LLM Data Leakage
MR-009.2

Data exfiltration via rendered output

#

The model is induced to emit private data through rendered elements such as markdown images or links that call out to an attacker.

MITRE ATLAS technique: AML.T0077 LLM Response Rendering
MR-009.3

Harvesting data from AI-enabled services

#

Access to the deployer's AI services is used to collect the data those services hold.

MITRE ATLAS technique: AML.T0085 Data from AI Services

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.