Decentralized Learning Robust to Data Poisoning Attacks

Yanwen Mao, Deepesh Data, Suhas Diggavi, Paulo Tabuada

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

2 Citations (Scopus)

Abstract

This paper addresses the problem of decentralized learning in the presence of data poisoning attacks. In this problem, we consider a collection of nodes connected through a network, each equipped with a local function. The objective is to compute the global minimizer of the aggregated local functions, in a decentralized manner, i.e., each node can only use its local function and data exchanged with nodes it is connected to. Moreover, each node is to agree on the said minimizer despite an adversary that can arbitrarily change the local functions of a fraction of the nodes. This problem setting has applications in robust learning, where nodes in a network are collectively training a model that minimizes the empirical loss with possibly attacked local data sets. In this paper, we propose a novel decentralized learning algorithm that enables all nodes to reach consensus on the optimal model, in the absence of attacks, and approximate consensus in the presence of data poisoning attacks.

Original languageEnglish
Title of host publication2022 IEEE 61st Conference on Decision and Control, CDC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6788-6793
Number of pages6
ISBN (Electronic)9781665467612
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event61st IEEE Conference on Decision and Control, CDC 2022 - Cancun, Mexico
Duration: 6 Dec 20229 Dec 2022

Publication series

NameProceedings of the IEEE Conference on Decision and Control
Volume2022-December
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370

Conference

Conference61st IEEE Conference on Decision and Control, CDC 2022
Country/TerritoryMexico
CityCancun
Period6/12/229/12/22

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Control and Optimization

Fingerprint

Dive into the research topics of 'Decentralized Learning Robust to Data Poisoning Attacks'. Together they form a unique fingerprint.

Cite this