ALEXANDRIA, Va., Aug. 12 -- United States Patent no. 12,705,345, issued on Aug. 11, was assigned to The Trustees of the University of Pennsylvania (Philadelphia).
"Methods, systems, and computer readable media for defending large language models (LLMs) against jailbreaking attacks" was invented by George J. Pappas (Wynnewood, Pa.), Alexander Beck Robey (Pittsburgh), Seyed Hamed Hassani (Philadelphia) and Eric Wong (Philadelphia).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method for defending an LLM against a jailbreaking attack includes receiving an input prompt for generating output from the LLM. The method further includes generating N versions of the input prompt, wherein generating each of the N ver...