ALEXANDRIA, Va., Dec. 23 -- United States Patent no. 12,505,648, issued on Dec. 23, was assigned to HiddenLayer Inc. (Austin, Texas).
"Multimodal AI model protection using embeddings" was invented by Ravikumar Balakrishnan (Beaverton, Ore.), Jason Martin (Beaverton, Ore.) and Andrew Davis (Portland, Ore.).
According to the abstract* released by the U.S. Patent & Trademark Office: "Techniques for assessing multi-modal inputs to a machine learning model involve receiving a multimodal input containing an image, producing several transformed versions of that image, and generating embeddings for both the original and transformed images. A pairwise similarity analysis among all embeddings is conducted to determine distance values. Two dissimila...