MECHANISM FOR POISON DETECTION IN A FEDERATED LEARNING SYSTEM

An apparatus is disclosed. The apparatus comprises one or more processors to receive trained model update data from each of a plurality of collaborators, execute an auxiliary machine learning model to the trained model update data to generate a risk score for trained model update data associated wit...

Full description

Saved in:
Bibliographic Details
Main Authors Nayshtut, Alex, Ben-Shalom, Omer, Kellermann, Raizy
Format Patent
LanguageEnglish
Published 14.04.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An apparatus is disclosed. The apparatus comprises one or more processors to receive trained model update data from each of a plurality of collaborators, execute an auxiliary machine learning model to the trained model update data to generate a risk score for trained model update data associated with each collaborator, apply one or more policies based on the risk scores to generate adjusted trained model update data associated with each collaborator.
Bibliography:Application Number: US202117558744