US Patent Issued to Microsoft Technology Licensing on Aug. 25 for "Detecting and mitigating prompt injection attacks on large language models" (Israeli Inventors)

ALEXANDRIA, Va., Aug. 25 -- United States Patent no. 12,717,919, issued on Aug. 25, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).

"Detecting and mitigating prompt injection attacks on large language models" was invented by Idan Hen (Tel Aviv, Israel) and Ron Keller (Ramat Hasharon, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for detecting and mitigating prompt injection attacks on a generative LLM are disclosed. A deployment scenario is considered, in which the generative LLM supports a task automation function. Prompts are received and interpreted by the generative LLM, and outputs from the generative LLM are used to trigger automation actions. The prompt...