Privacy Leakage in Federated Home Applications Using Gradient Inversion Algorithms

Wenzhi Chen, Hongjian Sun*, Minglei You, Jing Jiang

*Corresponding author for this work

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

1 Downloads (Pure)

Abstract

With advances in smart metering infrastructure, household electricity metering data are remotely collected, leading to concerns about household privacy leakage. Federated learning is a promising solution because it avoids direct data uploading. However, recent research shows that the gradient of federated learning contains a certain amount of private information that can be recovered using gradient inversion algorithms. This paper proposes an explainable algorithm to locate the key factors affecting privacy leakage and vulnerable data in home application scenarios. Simulations show comparative results of privacy leakages in different situations and reveal that for home Artificial Intelligence applications, smaller batch sizes, training iterations, and extreme values are prone to causing privacy leaks. Based on that, the advice for protecting federated learning privacy under gradient inversion algorithms is summarized.
Original languageEnglish
Title of host publicationICIT2024
Subtitle of host publicationThe 2024 International Conference on Industrial Technology (ICIT)
Place of PublicationPiscataway, US
PublisherIEEE
Number of pages6
ISBN (Print)9798350340266
DOIs
Publication statusPublished - 25 Mar 2024

Publication series

NameInternational Conference on Industrial Technology (ICIT)
PublisherIEEE
ISSN (Print)2641-0184
ISSN (Electronic)2643-2978

Cite this