US Patent Issued to HiddenLayer on May 27 for "Scanning and detecting threats in machine learning models" (British, American, Irish Inventors)

ALEXANDRIA, Va., June 17 -- United States Patent no. 12,314,380, issued on May 27, was assigned to HiddenLayer Inc. (Austin, Texas).

"Scanning and detecting threats in machine learning models" was invented by Tanner Burns (Austin, Texas), Chris Sestito (Austin, Texas), James Ballard (Fredricksburg, Va.), Thomas Bonner (Steeple Claydon, Great Britain), Marta Janus (Twickenham, Great Britain) and Eoin Wickens (Skibbereen, Ireland).

According to the abstract* released by the U.S. Patent & Trademark Office: "A machine learning model is scanned to detect actual or potential threats. The threats can be detected before execution of the machine learning model or during an isolated execution environment. The threat detection may include performing...