Baffle, Inc. (20250112768). PROTECTING SENSITIVE DATA IN TEXT-BASED GEN-AI SYSTEM
PROTECTING SENSITIVE DATA IN TEXT-BASED GEN-AI SYSTEM
Organization Name
Inventor(s)
Min-Hank Ho of Santa Clara CA US
Priyadarshan Kolte of Santa Clara CA US
Palanivel Rajan Shanmugavelayutham of Santa Clara CA US
Kishore Kumar Chandrasekaran of Santa Clara CA US
Balaji Govindan of Santa Clara CA US
PROTECTING SENSITIVE DATA IN TEXT-BASED GEN-AI SYSTEM
This abstract first appeared for US patent application 20250112768 titled 'PROTECTING SENSITIVE DATA IN TEXT-BASED GEN-AI SYSTEM
Original Abstract Submitted
a method and system for protecting sensitive data in a generative ai system is disclosed. the method includes encrypting sensitive data fields at a field level using a first encryption proxy in a data store, labeling the encrypted data fields with metadata in the data store, interfacing the data store to the generative ai system, receiving a user prompt at a second proxy, sending the user prompt to the generative ai system, generating a response by the generative ai system, receiving the response from the generative ai system, and selectively decrypting, by the second proxy, sensitive data in the response based on user authorization. in some embodiments, the metadata comprises encryption keys information and access control policies.