MLGuard: Mitigating Poisoning Attacks in Privacy Preserving Distributed Collaborative Learning

Youssef Khazbak, Tianxiang Tan, Guohong Cao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Distributed collaborative learning has enabled building machine learning models from distributed mobile users' data. It allows the server and users to collaboratively train a learning model where users only share model parameters with the server. To protect privacy, the server can use secure multiparty computation to learn the global model without revealing users' parameter updates in the clear. However this privacy preserving distributed learning opens the door to poisoning attacks, where malicious users poison their training data to maliciously influence the behavior of the global model. In this paper, we propose MLGuard, a privacy preserving distributed collaborative learning system with poisoning attack mitigation. MLGuard employs lightweight secret sharing scheme and a novel poisoning attack mitigation technique. We address several challenges such as preserving users' privacy, mitigating poisoning attacks, respecting resource constraints of mobile devices, and scaling to large number of users. Evaluation results demonstrate the effectiveness of MLGuard on building high accurate learning models with the existence of malicious users, while imposing minimal communication cost on mobile devices.

Original languageEnglish (US)
Title of host publicationICCCN 2020 - 29th International Conference on Computer Communications and Networks
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728166070
DOIs
StatePublished - Aug 2020
Event29th International Conference on Computer Communications and Networks, ICCCN 2020 - Honolulu, United States
Duration: Aug 3 2020Aug 6 2020

Publication series

NameProceedings - International Conference on Computer Communications and Networks, ICCCN
Volume2020-August
ISSN (Print)1095-2055

Conference

Conference29th International Conference on Computer Communications and Networks, ICCCN 2020
CountryUnited States
CityHonolulu
Period8/3/208/6/20

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Fingerprint Dive into the research topics of 'MLGuard: Mitigating Poisoning Attacks in Privacy Preserving Distributed Collaborative Learning'. Together they form a unique fingerprint.

Cite this