US Patent Issued to International Business Machines on Feb. 10 for "Artificial content identification using subset scanning over generative model activations" (Kenyan, Canadian Inventors)

ALEXANDRIA, Va., Feb. 11 -- United States Patent no. 12,547,899, issued on Feb. 10, was assigned to International Business Machines Corp. (Armonk, N.Y.).

"Artificial content identification using subset scanning over generative model activations" was invented by Celia Cintas (Nairobi, Kenya), Skyler Speakman (Nairobi, Kenya), Girmaw Abebe Tadesse (Nairobi, Kenya), Victor Abayomi Akinwande (Karen, Kenya) and Komminist Weldemariam (Ottawa).

According to the abstract* released by the U.S. Patent & Trademark Office: "A processor may receive input data. The processor may train a first machine learning model with the input data to extract a group of activation nodes. The processor may extract the group of activation nodes. The processor may dete...