Patent · US Active

Neural network confidentiality

US11829468B2 · kind B2 · utility

0Cited by

0References

26Claims

0Family size

Assignee

Telefonaktiebolaget LM Ericsson (Publ) · SE

Inventors

Jakob Sternby · Lund, SE
Björn Johansson · Lund, SE
Michael Liljenstam · Solna, SE

Key dates

Filing date	Dec 18, 2020
Grant date	Nov 28, 2023
Priority date	—
Expiry date	Jul 8, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/094
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A neural network having one or more public parts and one or more confidential parts is trained to perform a primary task. A deployment instantiation of the neural network is trained based on optimal performance of the primary task, and based on sub-optimal performance of the primary task conditioned on the confidential parts of the deployment instantiation being inaccessible. An adversary instantiation of the neural network is trained based on optimal performance of the primary task conditioned on the public parts being identical for the deployment instantiation and for the adversary instantiation, and conditioned on the confidential parts of the deployment instantiation being inaccessible. The training of the deployment instantiation and the training of the adversary instantiation are based on a plurality of training data samples, and are performed iteratively by alternating between the training of the deployment instantiation and the training of the adversary instantiation.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.