ScionFL: Efficient and Robust Secure Quantized Aggregation
Authors:
- 9 April 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 490-511
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.Keywords
All Related Versions
Funding Information
- VMware
This publication has 78 references indexed in Scilit:
- Prio+: Privacy Preserving Aggregate Statistics via Boolean Shares2022
- $\mathsf {FLOD}$: Oblivious Defender for Private Byzantine-Robust Federated Learning with Dishonest-Majority2021
- ATLAS: Efficient and Scalable MPC in the Honest Majority Setting2021
- Silver: Silent VOLE and Oblivious Transfer from Hardness of Decoding Structured LDPC Codes2021
- MArBled Circuits: Mixing Arithmetic and Boolean Circuits with Active Security2019
- Efficient Pseudorandom Correlation Generators: Silent OT Extension and More2019
- Turbospeedz: Double Your Online SPDZ! Improving SPDZ Using Function Dependent Preprocessing2019
- Secure Computation with Low Communication from Cross-Checking2018
- High-Throughput Secure Three-Party Computation for Malicious Adversaries and an Honest Majority2017
- Better Preprocessing for Secure Multiparty Computation2016