- Patent Title: Method for determining if a machine learning model has been copied
-
Application No.: US16250074Application Date: 2019-01-17
-
Publication No.: US11409845B2Publication Date: 2022-08-09
- Inventor: Nikita Veshchikov , Joppe Willem Bos , Simon Johann Friedberger
- Applicant: NXP B.V.
- Applicant Address: NL Eindhoven
- Assignee: NXP B.V.
- Current Assignee: NXP B.V.
- Current Assignee Address: NL Eindhoven
- Agent Daniel D. Hill
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06F21/12 ; G06K9/62 ; H04L9/32 ; G06F11/10

Abstract:
A method is provided for detecting copying of a machine learning model. A plurality of inputs is provided to a first machine learning model. The first machine learning model provides a plurality of output values. A sequence of bits of a master input is divided into a plurality of subsets of bits. The master input may be an image. Each subset of the plurality of subsets of bits corresponds to one of the plurality of output values. An ordered sequence of the inputs is generated based on the plurality of subsets of bits. The ordered sequence of the inputs is inputted to a second machine learning model. It is then determined if output values from the second machine learning model reproduces the predetermined master input. If the predetermined master input is reproduced, the second machine learning model is a copy of the first machine learning model.
Public/Granted literature
- US20200233936A1 METHOD FOR DETERMINING IF A MACHINE LEARNING MODEL HAS BEEN COPIED Public/Granted day:2020-07-23
Information query