FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregation

Marvin Xhemrishi, Johan Östman, Antonia Wachter-Zeh, Alexandre Graell i Amat

Primary Area: general machine learning (i.e., none of the above)

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: federated learning, malicious clients, data poisoning attacks, group testing, identification of malicious clients.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: In this work, we present a framework that allows to identify malicious clients in Federated Learning inspired by group testing, while still preserving clients' privacy.

Abstract:

We propose FedGT, a novel framework for identifying malicious clients in federated learning with secure aggregation.
Inspired by group testing, the framework leverages overlapping groups of clients to identify the presence of malicious clients in the groups via a decoding operation.
The clients identified as malicious are then removed from the training of the model, which is performed over the remaining clients.
By choosing the size, number, and overlap between groups, FedGT strikes a balance between privacy and security.
Specifically, the server learns the aggregated model of the clients in each group - vanilla federated learning and secure aggregation correspond to the extreme cases of FedGT with group size equal to one and the total number of clients, respectively.
The effectiveness of FedGT is demonstrated through extensive experiments on the MNIST, CIFAR-10, and ISIC2019 datasets in a cross-silo setting under different data-poisoning attacks.
These experiments showcase FedGT's ability to identify malicious clients, resulting in high model utility.
We further show that FedGT significantly outperforms the private robust aggregation approach based on the geometric median recently proposed by Pillutla et al. on heterogeneous client data (ISIC2019) and in the presence of targeted attacks (CIFAR-10 and ISIC2019).

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5593