US Patent Issued to AMAZON TECHNOLOGIES on Oct. 7 for "Security threat mitigation for large language models" (California, Washington, Massachusetts Inventors)

ALEXANDRIA, Va., Oct. 8 -- United States Patent no. 12,437,058, issued on Oct. 7, was assigned to AMAZON TECHNOLOGIES INC. (Seattle).

"Security threat mitigation for large language models" was invented by Jimit Majmudar (Sunnyvale, Calif.), Ben Smith (Laguna Beach, Calif.), Rahul Gupta (Waltham, Mass.), Sachin P. Joglekar (Bothell, Wash.) and Lili Gehorsam (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "Devices and techniques are generally described for security threat mitigation for generative machine learning models. In some examples, first request data including a first request may be received. First prompt data may be generated based at least in part on the first request data. First plan data may...