Skip to main content
Home/Risks/Weidinger et al. (2023)/Information & Safety Harms

Information & Safety Harms

Sociotechnical Safety Evaluation of Generative AI Systems

Weidinger 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.

"AI systems leaking, reproducing, generating or inferring sensitive, private, or hazardous information"(p. 14)

Other risks from Weidinger et al. (2023) (26)