DARR
Home / Navigator / MR-017
MR-017 Data, privacy & content liability System scope

Privacy-invasive inference and re-identification

The system infers sensitive attributes about, or re-identifies, individuals beyond what was explicitly provided.

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
7 entries across 6 papers
  • Bengio2025International AI Safety Report 202560.03.05
  • DSIT2023Capabilities and Risks from Frontier AI67.02.00
  • Gabriel2024The Ethics of Advanced AI Assistants24.08.03
  • IBM2025AI Risk Atlas65.11.03
  • Li2025A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents66.09.00
  • Weidinger2023Sociotechnical Safety Evaluation of Generative AI Systems18.03.00 18.03.02

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

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
1
  • A.8 ISO/IEC 23894 Annex A A.8
2
  • A.5.4 ISO/IEC 42001 Annex A A.5.4
  • A.7.5 ISO/IEC 42001 Annex A A.7.5
Cross-checksframeworks mapped in to test coverage
3
  • ibm-attribute-inference-attack Attribute inference attack
  • ibm-membership-inference-attack Membership inference attack
  • ibm-reidentification Reidentification
2
  • AISubtech-10.2.1 Model Inversion
  • AISubtech-8.1.1 Presence Detection
4
  • NISTAML.03 Privacy Compromises
  • NISTAML.032 Reconstruction partial
  • NISTAML.033 Membership Inference
  • NISTAML.034 Property Inference
1
  • GENAI.4 Data Privacy

More in Data, privacy & content liability

MR-009MR-011MR-013MR-024MR-039
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.