Large language model (llm) risk mitigation
AssigneeAmerican Express Travel Related Services Company, Inc.
InventorsHiranmayi Palanki, Shankar Djeyassilane
Life of this patent
Estimating the term…
Abstract
Disclosed are various approaches for large language model (LLM) application risk mitigation. A large language model (LLM) application along with a LLM risk mitigation program can be deployed. A system call for the LLM application is intercepted, in which the system interacts with a network LLM service using the LLM risk mitigation program. An LLM risk mitigation action is executed and modifies the system call using the LLM risk mitigation program based at least in part on a packet from the system call.
Claims20
A system, comprising:
- at least one computing device comprising at least one processor and at least one memory;
- and
- machine-readable instructions stored in the at least one memory that, when executed by the at least one processor, cause the at least one computing device to at least:
- deploy a large language model (LLM) application along with an LLM risk mitigation program;
- intercept a system call for the LLM application that interacts with a network LLM service using the LLM risk mitigation program;
- and
- execute an LLM risk mitigation action that modifies the system call using the LLM risk mitigation program based at least in part on a packet from the system call.
A non-transitory, computer-readable medium, comprising machine-readable instructions that, when executed by a processor of a computing device, cause the computing device to at least:
- deploy a large language model (LLM) application along with an LLM risk mitigation program,
- intercept a system call for the LLM application that interacts with a network LLM service using the LLM risk mitigation program;
- and
- execute an LLM risk mitigation action that modifies the system call using the LLM risk mitigation program based at least in part on a packet from the system call.
A method, comprising:
- identifying, via at least one computing device, a large language model (LLM) application that interacts with a network LLM service;
- generating, via the at least one computing device, an LLM risk mitigation code based at least in part on a portion of code from the LLM application that interfaces with the network LLM service;
- and
- deploying, via the at least one computing device, an LLM filtering program that implements the LLM risk mitigation code.
Dependencies are inferred from the claim text.