Invention Grant
- Patent Title: Distributed model generation via indirect private data access
-
Application No.: US17063359Application Date: 2020-10-05
-
Publication No.: US12093798B2Publication Date: 2024-09-17
- Inventor: Kevin Gidney
- Applicant: DocuSign, Inc.
- Applicant Address: US CA San Francisco
- Assignee: DocuSign, Inc.
- Current Assignee: DocuSign, Inc.
- Current Assignee Address: US CA San Francisco
- Agency: KDW FIRM PLLC
- Main IPC: G06N20/20
- IPC: G06N20/20 ; G06N5/04 ; H04L9/40

Abstract:
A computing system remotely trains a public ensemble model of an artificial intelligence model management system. The system receives, by the model management system, an encrypted representation of a private data value from a client system. The encrypted representation includes annotation information provided by the client system. The system determines, using the encrypted representation and the annotation information, a data value cluster that corresponds to the private data value. Data value clusters are generated using encrypted representations of a private data values provided by client systems. The system obtains, based on the assigned data value cluster, an encrypted representation of a model. The model is trained remotely by the client system using the private data value. The system adds the encrypted representation of the model to the public ensemble model. The public ensemble model is generated using a plurality of encrypted representations of models remotely trained by the client systems.
Public/Granted literature
- US20220108225A1 DISTRIBUTED MODEL GENERATION VIA INDIRECT PRIVATE DATA ACCESS Public/Granted day:2022-04-07
Information query