US Patent Issued to Dropbox on June 30 for "System and method for detecting prompt injection attacks to large language models" (California Inventor)

ALEXANDRIA, Va., July 16 -- United States Patent no. 12,670,253, issued on June 30, was assigned to Dropbox Inc. (San Francisco).

"System and method for detecting prompt injection attacks to large language models" was invented by Joshua Maddux (Irvine, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computing system receives a prompt to be provided as input to a large language model. The computing system generates generating an input string to the large language model by appending a plurality of contexts to the prompt. The plurality of contexts defines rules for the large language model to follow when generating the prompt. The plurality of contexts includes a negative context. Based on the prompt an...