Invention Grant
- Patent Title: Method for securing a machine learning based decision system
-
Application No.: US16640549Application Date: 2018-07-31
-
Publication No.: US11574245B2Publication Date: 2023-02-07
- Inventor: Frédéric Dao , Thomas Dandelot , Frédéric Paillart , Frédéric Faure , Fabrice Delhoste
- Applicant: THALES DIS FRANCE SAS
- Applicant Address: FR Meudon
- Assignee: THALES DIS FRANCE SAS
- Current Assignee: THALES DIS FRANCE SAS
- Current Assignee Address: FR Meudon
- Agency: Marc Boillot—Thales Dis CPL USA, Inc
- Priority: EP17306085 20170821
- International Application: PCT/EP2018/070743 WO 20180731
- International Announcement: WO2019/038036 WO 20190228
- Main IPC: G06N20/00
- IPC: G06N20/00 ; G06F21/44

Abstract:
A system configured to perform decision tasks carried out by a machine learning engine operates with a machine learning model, and includes a training component for improving the machine learning model, a device for carrying out decisions based on a set of input data, and an interaction interface for switching the machine learning model between training component and a device that includes a model attestation checker. The device performs acquiring input data, and ascertaining at least one machine learning model over the interaction interface. The model attestation checker performs checking if said machine learning model is trusted by a model attestation, and considering, for decision making, only those machine learning models that are trusted. The machine learning engine performs carrying out the decision task for input data by using a trusted machine learning model, and providing a result attestation for the decision output.
Public/Granted literature
- US20200219009A1 METHOD FOR SECURING A MACHINE LEARNING BASED DECISION SYSTEM Public/Granted day:2020-07-09
Information query