US Patent Issued to HiddenLayer on June 10 for "Detection of privacy attacks on machine learning models" (Canadian, British, American Inventors)

ALEXANDRIA, Va., June 18 -- United States Patent no. 12,328,331, issued on June 10, was assigned to HiddenLayer Inc. (Austin, Texas).

"Detection of privacy attacks on machine learning models" was invented by Hengrui Jia (Toronto), Ravikumar Balakrishnan (Beaverton, Ore.), Zeliang Kan (London) and Jason Martin (Beaverton, Ore.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A plurality of queries are input into an artificial intelligence (AI) model. The AI model is made up of a plurality of layers including an input layer, an output layer, and at least one intermediate layer between the input layer and the output layer. Each intermediate layer, during inference, can output a plurality of activations. Thereafte...