Skip to main content
Home/Risks/Deng et al. (2023)/Privacy and Data Leakage

Privacy and Data Leakage

Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements

Deng et al. (2023)

Category
Risk Domain

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 cause loss of confidential intellectual property.

Large pre-trained models trained on internet texts might contain private information like phone numbers, email addresses, and residential addresses.(p. 4)

Other risks from Deng et al. (2023) (6)