US Patent Issued to HiddenLayer on March 17 for "Adversarial attack detection based on similarity" (California, Oregon Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,580,957, issued on March 17, was assigned to HiddenLayer Inc. (Austin, Texas).

"Adversarial attack detection based on similarity" was invented by Julian Collado Umana (Irvine, Calif.) and Andrew Davis (Portland, Ore.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A query is received which is to be input into a machine learning model (or other artificial intelligence model). Thereafter, a plurality of historical queries of the machine learning model meeting first criteria relative to the query is determined using a first distance-based similarity analysis technique. Each of the historical queries have a known output by the machine learning model. An out...