US Patent Issued to HiddenLayer on Sept. 29 for "Detection of machine learning model attacks obfuscated in unicode" (Canadian, American Inventors)

ALEXANDRIA, Va., Sept. 30 -- United States Patent no. 12,750,400, issued on Sept. 29, was assigned to HiddenLayer Inc. (Austin, Texas).

"Detection of machine learning model attacks obfuscated in unicode" was invented by Kenneth Yeung (Ottawa) and Jason Martin (Beaverton, Ore.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A prompt for a generative artificial intelligence (GenAI) model which contains unicode is received. The prompt is then tokenized to result in a plurality of tokens. Token forming part of a repeating sequence are identified and then removed to result in a modified set of tokens. The modified set of tokens are subsequently detokenized to result in a modified prompt. It is then determined, whe...