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
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.
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.
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
5Expanded into this risk’s technique sub-risks.
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.
Crafted prompts induce the model to reveal sensitive data from its training set, context, or memory.
The model is induced to emit private data through rendered elements such as markdown images or links that call out to an attacker.
Access to the deployer's AI services is used to collect the data those services hold.
More in Data, privacy & content liability
See all Data, privacy & content liability 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.