Invention Grant
- Patent Title: Increasing security of neural networks by discretizing neural network inputs
-
Application No.: US16859789Application Date: 2020-04-27
-
Publication No.: US11354574B2Publication Date: 2022-06-07
- Inventor: Aurko Roy , Ian Goodfellow , Jacob Buckman , Colin Abraham Raffel
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06F17/16 ; G06N3/04

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for increasing the security of neural network by discretizing neural network inputs. One of the methods includes receiving a network input for a neural network; processing the network input using a discretization layer, wherein the discretization layer is configured to generate a discretized network input comprising a respective discretized vector for each of the numeric values in the network input; and processing the discretized network input using the plurality of additional neural network layers to generate a network output for the network input.
Public/Granted literature
- US20200257978A1 INCREASING SECURITY OF NEURAL NETWORKS BY DISCRETIZING NEURAL NETWORK INPUTS Public/Granted day:2020-08-13
Information query