Skip to main content
BackInference of private information
Home/Risks/Gabriel et al. (2024)/Inference of private information

Inference of private information

The Ethics of Advanced AI Assistants

Gabriel et al. (2024)

Sub-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.

"Finally, LLMs can in principle infer private information based on model inputs even if the relevant private information is not present in the training corpus (Weidinger et al., 2021). For example, an LLM may correctly infer sensitive characteristics such as race and gender from data contained in input prompts."(p. 133)

Part of Privacy

Other risks from Gabriel et al. (2024) (69)