MIT AI Risk Repository · Risk Sub-Category · 02.07.02

Memorization in LLMs

Category: Privacy Leakage

Description

"Memorization in LLMs refers to the capability to recover the training data with contextual prefixes. According to [88]–[90], given a PII entity x, which is memorized by a model F. Using a prompt p could force the model F to produce the entity x, where p and x exist in the training data. For instance, if the string “Have a good day!\n alice@email.com” is present in the training data, then the LLM could accurately predict Alice’s email when given the prompt “Have a good day!\n”."

From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI

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

Other entries from Cui2024