Deakin University
Browse

File(s) under permanent embargo

Federated Learning for Privacy Preservation of Healthcare Data from Smartphone-based Side-Channel Attacks

journal contribution
posted on 2022-09-29, 08:12 authored by A Rehman, Imran RazzakImran Razzak, G Xu
Federated learning has recently emerged as a striking framework for allowing machine and deep learning models with thousands of participants to have distributed training to preserve the privacy of users' data. Federated learning comes with the pros of allowing all participants the possibility of creating robust models even in the absence of sufficient training data. Meanwhile, the participants are allowed to stay anonymous in the process. Recently, Smartphone usage has increased on a huge scale due to its portability and ability to perform many daily life tasks. Typing on a smartphone's soft keyboard generates vibrations that could be abused to distinguish the typed keys, aiding side-channel attacks. This data can be in the form of clinical notes, medical information, username, and passwords. The attackers can steal this data using smartphone hardware sensors. This study proposes a novel framework based on federated learning for side-channel attack detection to secure this information. We collected a dataset from 10 Android smartphone users who were asked to type on the smartphone soft keyboard. We convert this dataset into two windows of five users to make two clients train local models. The federated learning-based framework aggregates model updates contributed by two clients and trains the DNN model individually on the dataset. To reduce the over-fitting factor, each client examines the findings three times. Experiments reveal that the DNN model has a higher accuracy of 80.09\%, showing that the proposed framework can efficiently detect side-channel attacks.

History

Journal

IEEE Journal of Biomedical and Health Informatics

Volume

27

Pagination

684-690

Location

Piscataway, N.J.

ISSN

2168-2194

eISSN

2168-2208

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Issue

2

Publisher

IEEE

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC