PromptRiskDBThreat intelligence atlas

Confidentiality loss

AI Risk

"Confidentiality loss - Unauthorised sharing of sensitive, confidential information and documents such as corporate strategy and financial plans with third-parties."

Overview

A source-backed snapshot of this AI risk.

Techniques2Attack methods connected to this risk.
Mitigations1Defenses that may help with related attacks.
Records2Source records unified into this concept.

Risk profile

How the MIT AI Risk Repository categorizes this risk.

Domain2. Privacy & Security
Subdomain2.0 > Privacy & Security; 2.1 > Compromise of privacy by leaking or correctly inferring sensitive information
Entity3 - Other; 4 - Not coded
Intent3 - Other; 4 - Not coded
Timing2 - Post-deployment; 4 - Not coded
CategoryFinancial and business
SubcategoryConfidentiality loss

Merged risk records

Source records unified into this canonical risk concept.

2 recordsView all →

MITRISK-Abercrombie2024-58.05.02 - Confidentiality loss

"Confidentiality loss - Unauthorised sharing of sensitive, confidential information and documents such as corporate strategy and financial plans with third-parties."

Domain2. Privacy & SecuritySubdomain2.0 > Privacy & SecuritySourceA Collaborative, Human-Centred Taxonomy of AI, Algorithmic, and Automation HarmsYear2024

MITRISK-Li2025-66.08.03 - Confidentiality loss

"Unauthorised sharing of sensitive, confidential information and documents such as corporate strategy and financial plans with third-parties, risking loss of market position or revenue"

Domain2. Privacy & SecuritySubdomain2.1 > Compromise of privacy by leaking or correctly inferring sensitive informationSourceA Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World IncidentsYear2025

Mitigations

Defenses that may help with related attacks.

LifecycleBusiness and Data Understanding + 2 moreCategoryPolicy
B&D UnderstandingData Preparation+1 more

Source evidence

Research source for this risk, when available.