Loading [MathJax]/extensions/MathZoom.js
Federated Learning for Privacy Preservation of Healthcare Data From Smartphone-Based Side-Channel Attacks | IEEE Journals & Magazine | IEEE Xplore

Federated Learning for Privacy Preservation of Healthcare Data From Smartphone-Based Side-Channel Attacks


Abstract:

Federated learning (FL) has recently emerged as a striking framework for allowing machine and deep learning models with thousands of participants to have distributed trai...Show More

Abstract:

Federated learning (FL) 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. Recently, smartphone usage has increased significantly 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 detect the typed keys, aiding side-channel attacks. Such data can be collected using smartphone hardware sensors during the entry of sensitive information such as clinical notes, personal medical information, username, and passwords. 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 training local models. The federated learning-based framework aggregates model updates contributed by two clients and trained the Deep Neural Network (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 achieves an accuracy of 80.09%, showing that the proposed framework has the potential to detect side-channel attacks.
Published in: IEEE Journal of Biomedical and Health Informatics ( Volume: 27, Issue: 2, February 2023)
Page(s): 684 - 690
Date of Publication: 03 May 2022

ISSN Information:

PubMed ID: 35503855

Funding Agency:


I. Introduction

The smartphone contains Personal Health Records (PHR) comprising data (i.e., family medical histories, past medical and surgical interventions, mental health data, physical activity data, heart rate data, and mood prediction) [1]–[3]. Studies [4]–[6] have shown that PHR data can be stolen using a smartphone’s hardware sensor. Regulatory requirements (i.e., General Data Protection Regulation (GDPR) [7], HIPAA [8]) can be met with the help of a newly emerging paradigm, Federated learning (FL), in the field of machine learning. While making use of benefits associated with massively distributed data, FL can mitigate privacy concerns [9]–[12]. FL helps the participants in collaborative training of a global model without sharing their local training data [12]. During each round of communication, all participants train local models based on their training data, and the model is then submitted to the server with updates. A global model is built by the server while employing a secure aggregation using the average of weights associated with local models [13], [14].

References

References is not available for this document.