公开(公告)号：US11048694B2

公开(公告)日：2021-06-29

申请号：US15963436

申请日：2018-04-26

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Vitaly Feldman ,  Thomas Steinke

IPC分类号： G06F16/2458 ,  G06F16/242 ,  G16H10/60 ,  G06N7/00 ,  G06N20/00 ,  G06F16/2457 ,  G06F16/27

摘要： A computer system may include a processor and a memory coupled thereto. The memory may include a database. The processor may be configured to randomly split the database into sub-databases and applying a database query to the sub-databases. The processor may also be configured to generate respective estimated query response values for each sub-database based upon applying the database query, calculate a median of the estimated query response values, and generate a probability distribution based upon the estimated query response values and the calculated median. The processor may further be configured to select a final estimated query response value based upon the probability distribution.

公开(公告)号：US20210409197A1

公开(公告)日：2021-12-30

申请号：US17472843

申请日：2021-09-13

申请人： International Business Machines Corporation

发明人： Nathalie Baracaldo Angel ,  Stacey Truex ,  Heiko H. Ludwig ,  Ali Anwar ,  Thomas Steinke ,  Rui Zhang

IPC分类号： H04L9/08 ,  H04L9/00 ,  G06F21/62 ,  G06N20/20 ,  G06F16/25 ,  G06F16/2458 ,  G06K9/62

摘要： Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.

公开(公告)号：US11139961B2

公开(公告)日：2021-10-05

申请号：US16405066

申请日：2019-05-07

申请人： International Business Machines Corporation

发明人： Nathalie Baracaldo Angel ,  Stacey Truex ,  Heiko H. Ludwig ,  Ali Anwar ,  Thomas Steinke ,  Rui Zhang

IPC分类号： H04L29/06 ,  H04L9/08 ,  H04L9/00 ,  G06F21/62 ,  G06N20/20 ,  G06F16/25 ,  G06F16/2458 ,  G06K9/62

摘要： Techniques regarding privacy preservation in a federated learning environment are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a plurality of machine learning components that can execute a machine learning algorithm to generate a plurality of model parameters. The computer executable components can also comprise an aggregator component that can synthesize a machine learning model based on an aggregate of the plurality of model parameters. The aggregator component can communicate with the plurality of machine learning components via a data privacy scheme that comprises a privacy process and a homomorphic encryption process in a federated learning environment.