MIT AI Risk Repository · Risk Sub-Category · 17.02.03

Risks from leaking or correctly inferring sensitive information

Category: Information Hazards

Open the MIT Risk Navigator All entries from Weidinger2021

Description

"LMs may provide true, sensitive information that is present in the training data. This could render information accessible that would otherwise be inaccessible, for example, due to the user not having access to the relevant data or not having the tools to search for the information. Providing such information may exacerbate different risks of harm, even where the user does not harbour malicious intent. In the future, LMs may have the capability of triangulating data to infer and reveal other secrets, such as a military strategy or a business secret, potentially enabling individuals with acces

From Ethical and social risks of harm from language models (Weidinger2021), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Domain: 2. Privacy & Security
Subdomain: 2.1 Compromise of privacy by obtaining, leaking or correctly inferring sensitive information
Causal entity: Other
Intent: Other
Timing: Post-deployment

Subdomain definition: AI systems that memorize and leak sensitive personal data or infer private information about individuals without their consent. Unexpected or unauthorized sharing of data and information can compromise user expectation of privacy, assist identity theft, or loss of confidential intellectual property.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Risks to privacy
International Scientific Report on the Safety of Advanced AI (Bengio2024)
Risks to privacy
International AI Safety Report 2025 (Bengio2025)
Privacy Leakage
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Private Training Data
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Memorization in LLMs
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Association in LLMs
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Privacy Leakage
Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)
Privacy and regulation violations
Navigating the Landscape of AI Ethics and Responsibility (Cunha2023)

Other entries from Weidinger2021

Discrimination, Exclusion and Toxicity Risk Category · 1.0
Social stereotypes and unfair discrmination Risk Sub-Category · 1.1
Social stereotypes and unfair discrmination Additional evidence
Exclusionary norms Risk Sub-Category · 1.1
Exclusionary norms Additional evidence
Exclusionary norms Additional evidence
Exclusionary norms Additional evidence
Toxic language Risk Sub-Category · 1.2
Lower performance for some languages and social groups Risk Sub-Category · 1.3
Lower performance for some languages and social groups Additional evidence
Information Hazards Risk Category · 2.1
Compromising privacy by leaking private infiormation Risk Sub-Category · 2.1