公开(公告)号：US11100222B2

公开(公告)日：2021-08-24

申请号：US16180144

申请日：2018-11-05

Applicant: NXP B.V.

Inventor： Marc Joye ,  Ahmed Ullah Qureshi

IPC: G06F21/55 ,  G06N3/02 ,  G06F21/75 ,  G06N20/00

Abstract: A method is provided for protecting a trained machine learning model that provides prediction results with confidence levels. The confidence level is a measure of the likelihood that a prediction is correct. The method includes determining if a query input to the model is an attempted attack on the model. If the query is determined to be an attempted attack, a first prediction result having a highest confidence level is swapped with a second prediction result having a relatively lower confidence level so that the first and second prediction results and confidence levels are re-paired. Then, the second prediction result is output from the model with the highest confidence level. By swapping the confidence levels and outputting the prediction results with the swapped confidence levels, the machine learning model is more difficult for an attacker to extract.