Creative Commons Attribution 4.0 license (CC BY 4.0)when quoting this document, please refer to the following
DOI: 10.4230/LIPIcs.FORC.2022.7
URN: urn:nbn:de:0030-drops-165302
URL: https://drops.dagstuhl.de/opus/volltexte/2022/16530/
Talwar, Kunal
Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation
| pdf-format: |
|
Abstract
Computing the noisy sum of real-valued vectors is an important primitive in differentially private learning and statistics. In private federated learning applications, these vectors are held by client devices, leading to a distributed summation problem. Standard Secure Multiparty Computation protocols for this problem are susceptible to poisoning attacks, where a client may have a large influence on the sum, without being detected.In this work, we propose a poisoning-robust private summation protocol in the multiple-server setting, recently studied in PRIO [Henry Corrigan-Gibbs and Dan Boneh, 2017]. We present a protocol for vector summation that verifies that the Euclidean norm of each contribution is approximately bounded. We show that by relaxing the security constraint in SMC to a differential privacy like guarantee, one can improve over PRIO in terms of communication requirements as well as the client-side computation. Unlike SMC algorithms that inevitably cast integers to elements of a large finite field, our algorithms work over integers/reals, which may allow for additional efficiencies.
BibTeX - Entry
@InProceedings{talwar:LIPIcs.FORC.2022.7,
author = {Talwar, Kunal},
title = {{Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation}},
booktitle = {3rd Symposium on Foundations of Responsible Computing (FORC 2022)},
pages = {7:1--7:16},
series = {Leibniz International Proceedings in Informatics (LIPIcs)},
ISBN = {978-3-95977-226-6},
ISSN = {1868-8969},
year = {2022},
volume = {218},
editor = {Celis, L. Elisa},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/opus/volltexte/2022/16530},
URN = {urn:nbn:de:0030-drops-165302},
doi = {10.4230/LIPIcs.FORC.2022.7},
annote = {Keywords: Zero Knowledge, Secure Summation, Differential Privacy}
}
| Keywords: | Zero Knowledge, Secure Summation, Differential Privacy | |
| Seminar: | 3rd Symposium on Foundations of Responsible Computing (FORC 2022) | |
| Issue date: | 2022 | |
| Date of publication: | 15.07.2022 |
