ScionFL: Efficient and Robust Secure Quantized Aggregation

Yaniv Ben-Itzhak, Helen Mollering, Benny Pinkas, Thomas Schneider, Ajith Suresh, Oleksandr Tkachenko, Shay Vargaftik, Christian Weinert, Hossein Yalame, Avishay Yanai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Secure aggregation is commonly used in federated learning (FL) to alleviate privacy concerns related to the central aggregator seeing all parameter updates in the clear. Unfortunately, most existing secure aggregation schemes ignore two critical orthogonal research directions that aim to (i) significantly reduce client-server communication and (ii) mitigate the impact of malicious clients. However, both of these additional properties are essential to facilitate cross-device FL with thousands or even millions of (mobile) participants.In this paper, we unite both research directions by introducing ScionFL, the first secure aggregation framework for FL that operates efficiently on quantized inputs and simultaneously provides robustness against malicious clients. Our framework leverages (novel) multi-party computation (MPC) techniques and supports multiple linear (1-bit) quantization schemes, including ones that utilize the randomized Hadamard transform and Kashin's representation.Our theoretical results are supported by extensive evaluations. We show that with no overhead for clients and moderate overhead for the server compared to transferring and processing quantized updates in plaintext, we obtain comparable accuracy for standard FL benchmarks. Moreover, we demonstrate the robustness of our framework against state-of-the-art poisoning attacks.

Original languageEnglish
Title of host publicationProceedings - IEEE Conference on Safe and Trustworthy Machine Learning, SaTML 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages490-511
Number of pages22
ISBN (Electronic)9798350349504
DOIs
StatePublished - 2024
Event2024 IEEE Conference on Safe and Trustworthy Machine Learning, SaTML 2024 - Toronto, Canada
Duration: 9 Apr 202411 Apr 2024

Publication series

NameProceedings - IEEE Conference on Safe and Trustworthy Machine Learning, SaTML 2024

Conference

Conference2024 IEEE Conference on Safe and Trustworthy Machine Learning, SaTML 2024
Country/TerritoryCanada
CityToronto
Period9/04/2411/04/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Fingerprint

Dive into the research topics of 'ScionFL: Efficient and Robust Secure Quantized Aggregation'. Together they form a unique fingerprint.

Cite this