US Patent Issued to HiddenLayer on Sept. 1 for "Machine learning model adversarial attack monitoring" (Canadian, American Inventors)

ALEXANDRIA, Va., Sept. 1 -- United States Patent no. 12,724,883, issued on Sept. 1, was assigned to HiddenLayer Inc. (Austin, Texas).

"Machine learning model adversarial attack monitoring" was invented by Tanner Burns (Austin, Texas), Chris Sestito (Austin, Texas) and James Ballard (Ottawa).

According to the abstract* released by the U.S. Patent & Trademark Office: "Adversarial attacks on a machine learning model are detected by receiving vectorized data input into the machine learning model along with outputs of the machine learning model responsive to the vectorized data. The vectorized data corresponds to a plurality of queries of the machine learning model by a requesting user. A confidence level is determined which characterizes a li...