Patent · US Active

Byzantine-robust federated learning

US12175338B2 · kind B2 · utility

0Cited by
4References
13Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 9, 2021
Grant dateDec 24, 2024
Priority date
Expiry dateOct 28, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2221/033
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A federated learning method comprises creating a log of previously provided gradients from a plurality of workers, receiving updated gradients from the plurality of workers, calculating a vulnerability weight for each layer of a global machine learning model using the updated gradients, calculating an aggregated gradient using the vulnerability weight and the updated gradients, and updating the global machine learning model using the aggregated gradient. Some embodiments may also determine whether a Byzantine attack is occurring based upon the calculated aggregated gradient. An apparatus and computer program product may be used to implement the method.

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