Protecting sensitive data used by large language models
AssigneeAcronis International GmbH
InventorsSerg Bell, Stanislav Protasov
Life of this patent
Estimating the term…
Abstract
Systems and methods for protecting certain personal data used by large language models. A user can ask artificial intelligence to provide an answer that can include personal or sensitive data. Systems and methods determine which data is restricted and personal, and which data is not. Personal or sensitive data is handled according to handling rules.
Claims20
A method for protecting sensitive data, the method comprising:
- generating a rule set for handling sensitive data;
- receiving, via a natural language processing tool, a request from a user;
- retrieving data associated with the request, wherein the data includes at least one of text data, image data, video data, audio data, virtual reality data, or gesture data;
- determining a sensitive data portion of the data;
- labeling the sensitive data portion of the data;
- operating on the sensitive data portion according to the rule set based on the labeling to generate modified data;
- and
- returning the modified data to the user.
A system for protecting sensitive data, the system comprising:
- computing hardware of at least one processor and memory operably coupled to the at least one processor;
- and
- instructions that, when executed on the computing hardware, cause the computing hardware to implement:
- a natural language processing tool configured to receive a request from a user,
- a data management engine configured to retrieve data associated with the request and label sensitive data portion of the data, wherein the data includes at least one of text data, image data, video data, audio data, virtual reality data, or gesture data,
- a detection engine configured to determine a sensitive data portion of the data,
- a handling engine configured to generate a rule set and operate on the sensitive data portion according to the rule set based on the labeling to generate modified data, and
- wherein the natural language processing tool is further configured to return the modified data to the user.
A machine learning model trained on training data of a plurality of previous natural language requests including a plurality of previous sensitive data, the machine learning model configured to:
- receive a natural language request from a user;
- determine data associated with the request;
- determine a sensitive data portion of the data;
- determine a handling instruction for the sensitive data portion;
- and
- return the sensitive data portion to the user according to the handling instruction.
Dependencies are inferred from the claim text.