Sensitive information leakage through model outputs

https://taxonomy.eticas.ai/risk/sensitive-information-leakage

Maturity: established

Personal or confidential/proprietary information present in training data, inference-time context, or connected systems, surfacing in model outputs through memorisation, context disclosure, cross-tenant contamination, or system-prompt extraction. Covers personal data and organisational or commercial confidentiality alike.

Also known as: PII leakage rate · Privacy leakage

System type: ADM and LLM systems
Lifecycle stages: In Processing, Post Processing

Mappings to external frameworks

Standards & frameworks

Framework Reference
EU AI Act (Regulation 2024/1689) Article 15(5) — resilience against attempts by unauthorized third parties to alter use, outputs or performance
AIUC-1 — AI Underwriting Company Standard Prevent PII leakage
Council of Europe Framework Convention on AI (CETS No. 225) Article 11(a)
NIST AI 600-1 — Generative AI Risk Profile Data Privacy
TC260 AI Safety Governance Framework (v2.0) §3.1.2(d) Data and personal information leakage

Taxonomies & vocabularies

Framework Reference
MIT AI Risk Repository Compromise of privacy by obtaining, leaking or correctly inferring sensitive information
AIR 2024 Unauthorized disclosure
W3C Data Privacy Vocabulary — AI Extension Unauthorised Data Disclosure

Source: HRA project taxonomy