Invention Grant
- Patent Title: Artificial neural network integrity verification
-
Application No.: US16229044Application Date: 2018-12-21
-
Publication No.: US11454968B2Publication Date: 2022-09-27
- Inventor: Alberto Troia , Antonino Mondello , Michelangelo Pisasale
- Applicant: Micron Technology, Inc.
- Applicant Address: US ID Boise
- Assignee: Micron Technology, Inc.
- Current Assignee: Micron Technology, Inc.
- Current Assignee Address: US ID Boise
- Agency: Brooks, Cameron & Huebsch, PLLC
- Main IPC: G05D1/00
- IPC: G05D1/00 ; H04L9/32 ; G06N3/063 ; G06F11/10 ; G06F17/16 ; G06F21/00

Abstract:
An example method comprises receiving a number of inputs to a system employing an artificial neural network (ANN), wherein the ANN comprises a number of ANN partitions each having respective weight matrix data and bias data corresponding thereto stored in a memory. The method includes: determining an ANN partition to which the number of inputs correspond, reading, from the memory the weight matrix data and bias data corresponding to the determined ANN partition, and a first cryptographic code corresponding to the determined ANN partition; generating, using the weight matrix data and bias data read from the memory, a second cryptographic code corresponding to the determined ANN partition; determining whether the first cryptographic code and the second cryptographic code match; and responsive to determining a mismatch between the first cryptographic code and the second cryptographic code, issuing an indication of the mismatch to a controller of the system.
Public/Granted literature
- US20190265701A1 ARTIFICIAL NEURAL NETWORK INTEGRITY VERIFICATION Public/Granted day:2019-08-29
Information query