PRIVACY-PRESERVING PROMPT ENGINEERING FOR GENERATIVE ARTIFICIAL INTELLIGENCE

Abstract: certain aspects of the disclosure concern a computer-implemented method for improved data security when interacting with a large language model. the method includes receiving a prompt query entered through a user interface, detecting sensitive data in the prompt query that violates a security protocol, generating a modified prompt query which anonymizes the sensitive data, submitting the modified prompt query to a large language model, and receiving a reply generated by the large language model. the reply contains anonymized sensitive data. the method further includes generating a modified reply which deanonymizes the anonymized sensitive data and presenting the modified reply on the user interface.

Inventor(s): Laurent Gomez

CPC Classification: G06F21/6254 ({by anonymising data, e.g. decorrelating personal data from the owner's identification})

Search for rejections for patent application number 20250165648