Data Security Challenges in Deep Neural Network for Healthcare IoT Systems

Edmond S. L. Ho

doi:10.1007/978-3-030-85428-7_2

Data Security Challenges in Deep Neural Network for Healthcare IoT Systems

Edmond S. L. Ho^*

^*Corresponding author for this work

Computer Information Sciences Department

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

8 Citations (Scopus)

13 Downloads (Pure)

Abstract

With the advancement of IoT technology, more and more healthcare applications were developed in recent years. In addition to the traditional sensor-based systems, image-based healthcare IoT systems become more popular since no specialized sensors are required. Combining with Deep Neural Network (DNN) based automated diagnosis and decision-making systems, it is possible to provide users with 24/7 health monitoring in real life. However, the high computational cost for training DNNs can be a hurdle for developing such kind of powerful systems. While cloud computing can be a feasible solution, uploading training data for the DNN models to the cloud may lead to data security issues. In this chapter, we will review some image-based healthcare IoT systems and discuss some potential risks on data security when training the DNN models on the cloud.

Original language	English
Title of host publication	Security and Privacy Preserving for IoT and 5G Networks
Subtitle of host publication	Techniques, Challenges, and New Directions
Editors	Ahmed A. Abd El-Latif, Bassem Abd-El-Atty, SSalvador E. Venegas-Andraca, Wojciech Mazurczyk, Brij B. Gupta
Place of Publication	Cham, Switzerland
Publisher	Springer
Chapter	2
Pages	19-37
Number of pages	19
Volume	95
ISBN (Electronic)	9783030854287
ISBN (Print)	9783030854270, 9783030854300
DOIs	https://doi.org/10.1007/978-3-030-85428-7_2
Publication status	Published - 2022

Publication series

Name	Studies in Big Data
Publisher	Springer
Volume	95
ISSN (Print)	2197-6503
ISSN (Electronic)	2197-6511

Access to Document

10.1007/978-3-030-85428-7_2

_IoT5GCyber_final____Data_Security_Challenges_in_Deep_Neural_Network_for_Healthcare_IoT_SystemsAccepted author manuscript, 8.42 MB

Cite this

Ho, E. S. L. (2022). Data Security Challenges in Deep Neural Network for Healthcare IoT Systems. In A. A. Abd El-Latif, B. Abd-El-Atty, SS. E. Venegas-Andraca, W. Mazurczyk, & B. B. Gupta (Eds.), Security and Privacy Preserving for IoT and 5G Networks: Techniques, Challenges, and New Directions (Vol. 95, pp. 19-37). (Studies in Big Data; Vol. 95). Springer. https://doi.org/10.1007/978-3-030-85428-7_2

Ho, Edmond S. L. / Data Security Challenges in Deep Neural Network for Healthcare IoT Systems. Security and Privacy Preserving for IoT and 5G Networks: Techniques, Challenges, and New Directions. editor / Ahmed A. Abd El-Latif ; Bassem Abd-El-Atty ; SSalvador E. Venegas-Andraca ; Wojciech Mazurczyk ; Brij B. Gupta. Vol. 95 Cham, Switzerland : Springer, 2022. pp. 19-37 (Studies in Big Data).

@inbook{22878e25557745dbb9674c804af3701d,

title = "Data Security Challenges in Deep Neural Network for Healthcare IoT Systems",

abstract = "With the advancement of IoT technology, more and more healthcare applications were developed in recent years. In addition to the traditional sensor-based systems, image-based healthcare IoT systems become more popular since no specialized sensors are required. Combining with Deep Neural Network (DNN) based automated diagnosis and decision-making systems, it is possible to provide users with 24/7 health monitoring in real life. However, the high computational cost for training DNNs can be a hurdle for developing such kind of powerful systems. While cloud computing can be a feasible solution, uploading training data for the DNN models to the cloud may lead to data security issues. In this chapter, we will review some image-based healthcare IoT systems and discuss some potential risks on data security when training the DNN models on the cloud.",

author = "Ho, {Edmond S. L.}",

note = "Funding information: This project is supported by the Royal Society (Ref: IES/R1/191147).",

year = "2022",

doi = "10.1007/978-3-030-85428-7_2",

language = "English",

isbn = "9783030854270",

volume = "95",

series = "Studies in Big Data",

publisher = "Springer",

pages = "19--37",

editor = "{Abd El-Latif}, {Ahmed A.} and Bassem Abd-El-Atty and Venegas-Andraca, {SSalvador E.} and Wojciech Mazurczyk and Gupta, {Brij B.}",

booktitle = "Security and Privacy Preserving for IoT and 5G Networks",

address = "Germany",

}

Ho, ESL 2022, Data Security Challenges in Deep Neural Network for Healthcare IoT Systems. in AA Abd El-Latif, B Abd-El-Atty, SSE Venegas-Andraca, W Mazurczyk & BB Gupta (eds), Security and Privacy Preserving for IoT and 5G Networks: Techniques, Challenges, and New Directions. vol. 95, Studies in Big Data, vol. 95, Springer, Cham, Switzerland, pp. 19-37. https://doi.org/10.1007/978-3-030-85428-7_2

Data Security Challenges in Deep Neural Network for Healthcare IoT Systems. / Ho, Edmond S. L.
Security and Privacy Preserving for IoT and 5G Networks: Techniques, Challenges, and New Directions. ed. / Ahmed A. Abd El-Latif; Bassem Abd-El-Atty; SSalvador E. Venegas-Andraca; Wojciech Mazurczyk; Brij B. Gupta. Vol. 95 Cham, Switzerland: Springer, 2022. p. 19-37 (Studies in Big Data; Vol. 95).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - Data Security Challenges in Deep Neural Network for Healthcare IoT Systems

AU - Ho, Edmond S. L.

N1 - Funding information: This project is supported by the Royal Society (Ref: IES/R1/191147).

PY - 2022

Y1 - 2022

N2 - With the advancement of IoT technology, more and more healthcare applications were developed in recent years. In addition to the traditional sensor-based systems, image-based healthcare IoT systems become more popular since no specialized sensors are required. Combining with Deep Neural Network (DNN) based automated diagnosis and decision-making systems, it is possible to provide users with 24/7 health monitoring in real life. However, the high computational cost for training DNNs can be a hurdle for developing such kind of powerful systems. While cloud computing can be a feasible solution, uploading training data for the DNN models to the cloud may lead to data security issues. In this chapter, we will review some image-based healthcare IoT systems and discuss some potential risks on data security when training the DNN models on the cloud.

AB - With the advancement of IoT technology, more and more healthcare applications were developed in recent years. In addition to the traditional sensor-based systems, image-based healthcare IoT systems become more popular since no specialized sensors are required. Combining with Deep Neural Network (DNN) based automated diagnosis and decision-making systems, it is possible to provide users with 24/7 health monitoring in real life. However, the high computational cost for training DNNs can be a hurdle for developing such kind of powerful systems. While cloud computing can be a feasible solution, uploading training data for the DNN models to the cloud may lead to data security issues. In this chapter, we will review some image-based healthcare IoT systems and discuss some potential risks on data security when training the DNN models on the cloud.

UR - https://www.springer.com/gp/book/9783030854270

UR - http://www.scopus.com/inward/record.url?scp=85129461286&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-85428-7_2

DO - 10.1007/978-3-030-85428-7_2

M3 - Chapter

SN - 9783030854270

SN - 9783030854300

VL - 95

T3 - Studies in Big Data

SP - 19

EP - 37

BT - Security and Privacy Preserving for IoT and 5G Networks

A2 - Abd El-Latif, Ahmed A.

A2 - Abd-El-Atty, Bassem

A2 - Venegas-Andraca, SSalvador E.

A2 - Mazurczyk, Wojciech

A2 - Gupta, Brij B.

PB - Springer

CY - Cham, Switzerland

ER -

Ho ESL. Data Security Challenges in Deep Neural Network for Healthcare IoT Systems. In Abd El-Latif AA, Abd-El-Atty B, Venegas-Andraca SSE, Mazurczyk W, Gupta BB, editors, Security and Privacy Preserving for IoT and 5G Networks: Techniques, Challenges, and New Directions. Vol. 95. Cham, Switzerland: Springer. 2022. p. 19-37. (Studies in Big Data). Epub 2021 Oct 10. doi: 10.1007/978-3-030-85428-7_2

Data Security Challenges in Deep Neural Network for Healthcare IoT Systems

Abstract

Publication series

Access to Document

Other files and links

Fingerprint

Cite this