Robust Federated Learning with Attack-Adaptive Aggregation

MPhil Thesis Defence


Title: "Robust Federated Learning with Attack-Adaptive Aggregation"

By

Mr. Ching Pui WAN


Abstract

In this thesis, we discuss a data-driven approach to defend adversarial 
attacks in federated learning. Federated learning is vulnerable to various 
attacks, such as model poisoning and backdoor attacks, even if some 
existing defense strategies are used. To address this challenge, we 
propose an attack-adaptive aggregation strategy to defend against various 
attacks for robust federated learning. The proposed approach is based on 
training a neural network with an attention mechanism that learns the 
vulnerability of federated learning models from a set of plausible 
attacks. Our aggregation strategy can be adapted to defend against various 
attacks in a data-driven fashion. Our approach has achieved competitive 
performance in defending model poisoning and backdoor attacks in federated 
learning tasks on images and text datasets.


Date:  			Tuesday, 29 June 2021

Time:			10:00am - 12:00noon

Zoom meeting: 
https://hkust.zoom.us/j/95333855525?pwd=YmNLVnFESjJ1bGl6SHFpSVFsN1B4QT09

Committee Members:	Dr. Qifeng Chen (Supervisor)
 			Dr. Kai Chen (Chairperson)
 			Dr. Wei Wang

**** ALL are Welcome ****