skip to main content

Attention:

The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, October 10 until 2:00 AM ET on Friday, October 11 due to maintenance. We apologize for the inconvenience.


This content will become publicly available on July 21, 2025

Title: FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error
Award ID(s):
1937786 2131859
NSF-PAR ID:
10522911
Author(s) / Creator(s):
; ;
Publisher / Repository:
International Conference on Machine Learning
Date Published:
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Model species continue to underpin groundbreaking plant science research. At the same time, the phylogenetic resolution of the land plant Tree of Life continues to improve. The intersection of these two research paths creates a unique opportunity to further extend the usefulness of model species across larger taxonomic groups. Here we promote the utility of the Arabidopsis thaliana model species, especially the ability to connect its genetic and functional resources, to species across the entire Brassicales order. We focus on the utility of using genomics and phylogenomics to bridge the evolution and diversification of several traits across the Brassicales to the resources in Arabidopsis, thereby extending scope from a model species by establishing a “model clade”. These Brassicales-wide traits are discussed in the context of both the model species Arabidopsis thaliana and the family Brassicaceae. We promote the utility of such a “model clade” and make suggestions for building global networks to support future studies in the model order Brassicales.

     
    more » « less