ALEXANDRIA, Va., July 28 -- United States Patent no. 12,694,094, issued on July 28, was assigned to Cisco Technology Inc. (San Jose, Calif.).

"System and method for advanced countermeasures against prompt injection attacks in large language models" was invented by Nikhil Sainath Kale (Marina, Calif.), John H. Hess III (Phoenix), Shankar Ramanathan (Allen, Texas), Foster G. Lipkey (New Market, Md.) and John J. Groetzinger (Baltimore).

According to the abstract* released by the U.S. Patent & Trademark Office: "In an embodiment, a method includes receiving a prompt provided to a large language model (LLM), generating a semantic fingerprint for the prompt based on semantic and syntactic features associated with the prompt, generating a vector...