FedClean: A Defense Mechanism against Parameter Poisoning Attacks in Federated Learning

Abhishek Kumar; Vivek Khimani; Dimitris Chatzopoulos; Pan Hui

ICASSP 2022accepted0 citations

FedClean: A Defense Mechanism against Parameter Poisoning Attacks in Federated Learning

Abhishek Kumar, Vivek Khimani, Dimitris Chatzopoulos, Pan Hui

Abstract

In Federated learning (FL) systems, a centralized entity (server), instead of access to the training data, has access to model parameter updates computed by each participant independently and based solely on their samples. Unfortunately, FL is susceptible to model poisoning attacks, in which malicious or malfunctioning entities share polluted updates that can compromise the model’s accuracy. In this study, we propose FedClean, an FL mechanism that is robust to model poisoning attacks. The accuracy of the models trained with the assistance of FedClean is close to the one where malicious entities do not participate.

BibTeX

@inproceedings{icassp2022_fedcleanadefense,
  title = {FedClean: A Defense Mechanism against Parameter Poisoning Attacks in Federated Learning},
  author = {Abhishek Kumar and Vivek Khimani and Dimitris Chatzopoulos and Pan Hui},
  booktitle = {ICASSP 2022},
  year = {2022}
}