公开(公告)号：US11410078B2

公开(公告)日：2022-08-09

申请号：US16297955

申请日：2019-03-11

Applicant: NXP B.V.

Inventor： Joppe Willem Bos ,  Simon Johann Friedberger ,  Christiaan Kuipers ,  Vincent Verneuil ,  Nikita Veshchikov ,  Christine Van Vredendaal ,  Brian Ermans

IPC: G06N20/00 ,  H04L9/08 ,  H04L9/32

Abstract: A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.

公开(公告)号：US20200293941A1

公开(公告)日：2020-09-17

申请号：US16297955

申请日：2019-03-11

Applicant: NXP B.V.

Inventor： Joppe Willem Bos ,  Simon Johann Friedberger ,  Christiaan Kuipers ,  Vincent Verneuil ,  Nikita Veshchikov ,  Christine Van Vredendaal ,  Brian Ermans

IPC: G06N20/00 ,  H04L9/08 ,  H04L9/32

Abstract: A method and data processing system for making a machine learning model more resistant to adversarial examples are provided. In the method, an input for a machine learning model is provided. A randomly generated mask is added to the input to produce a modified input. The modified input is provided to the machine learning model. The randomly generated mask negates the effect of a perturbation added to the input for causing the input to be an adversarial example. The method may be implemented using the data processing system.