Privacy-preserving quantum machine learning using differential privacy

Makhamisa Senekane; Mhlambululi Mafu; Benedict Molibeli Taele

doi:10.1109/AFRCON.2017.8095692

Privacy-preserving quantum machine learning using differential privacy

Makhamisa Senekane, Mhlambululi Mafu, Benedict Molibeli Taele

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

The advance of artificial intelligence in general and machine learning in particular has resulted in the need to pay more attention to the provision of privacy to the data being anlyzed. An example of sensitive data analysis might be in the analysis of individuals' medical records. In such a case, there might be a need to draw insights from data while at the same time maintaining privacy of the participants. Such cases have given birth to privacy-preserving data analyitics. Privacy is typically guaranteed by a differentially private mechanism. In this paper, we present a novel mechanism for privacy-preserving quantum machine learning. The mechanism is tested on the sensitive dataset that contains features and target labels for breast cancer prediction. The results obtained underline the utility of this mechanism.

Original language	English
Title of host publication	2017 IEEE AFRICON
Subtitle of host publication	Science, Technology and Innovation for Africa, AFRICON 2017
Editors	Darryn R. Cornish
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1432-1435
Number of pages	4
ISBN (Electronic)	9781538627754
DOIs	https://doi.org/10.1109/AFRCON.2017.8095692
Publication status	Published - Nov 3 2017
Event	IEEE AFRICON 2017 - Cape Town, South Africa Duration: Sept 18 2017 → Sept 20 2017

Publication series

Name	2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017

Conference

Conference	IEEE AFRICON 2017
Country/Territory	South Africa
City	Cape Town
Period	9/18/17 → 9/20/17

All Science Journal Classification (ASJC) codes

Human-Computer Interaction
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence
Computer Networks and Communications
Computer Science Applications

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/AFRCON.2017.8095692

Cite this

Senekane, M., Mafu, M., & Taele, B. M. (2017). Privacy-preserving quantum machine learning using differential privacy. In D. R. Cornish (Ed.), 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017 (pp. 1432-1435). Article 8095692 (2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AFRCON.2017.8095692

Senekane, Makhamisa ; Mafu, Mhlambululi ; Taele, Benedict Molibeli. / Privacy-preserving quantum machine learning using differential privacy. 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. editor / Darryn R. Cornish. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1432-1435 (2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017).

@inproceedings{a5b7bbd1f7654ea583f0ba1e618cbe05,

title = "Privacy-preserving quantum machine learning using differential privacy",

abstract = "The advance of artificial intelligence in general and machine learning in particular has resulted in the need to pay more attention to the provision of privacy to the data being anlyzed. An example of sensitive data analysis might be in the analysis of individuals' medical records. In such a case, there might be a need to draw insights from data while at the same time maintaining privacy of the participants. Such cases have given birth to privacy-preserving data analyitics. Privacy is typically guaranteed by a differentially private mechanism. In this paper, we present a novel mechanism for privacy-preserving quantum machine learning. The mechanism is tested on the sensitive dataset that contains features and target labels for breast cancer prediction. The results obtained underline the utility of this mechanism.",

author = "Makhamisa Senekane and Mhlambululi Mafu and Taele, {Benedict Molibeli}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; IEEE AFRICON 2017 ; Conference date: 18-09-2017 Through 20-09-2017",

year = "2017",

month = nov,

day = "3",

doi = "10.1109/AFRCON.2017.8095692",

language = "English",

series = "2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1432--1435",

editor = "Cornish, {Darryn R.}",

booktitle = "2017 IEEE AFRICON",

address = "United States",

}

Senekane, M, Mafu, M & Taele, BM 2017, Privacy-preserving quantum machine learning using differential privacy. in DR Cornish (ed.), 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017., 8095692, 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017, Institute of Electrical and Electronics Engineers Inc., pp. 1432-1435, IEEE AFRICON 2017, Cape Town, South Africa, 9/18/17. https://doi.org/10.1109/AFRCON.2017.8095692

Privacy-preserving quantum machine learning using differential privacy. / Senekane, Makhamisa; Mafu, Mhlambululi; Taele, Benedict Molibeli.
2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. ed. / Darryn R. Cornish. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1432-1435 8095692 (2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Privacy-preserving quantum machine learning using differential privacy

AU - Senekane, Makhamisa

AU - Mafu, Mhlambululi

AU - Taele, Benedict Molibeli

PY - 2017/11/3

Y1 - 2017/11/3

N2 - The advance of artificial intelligence in general and machine learning in particular has resulted in the need to pay more attention to the provision of privacy to the data being anlyzed. An example of sensitive data analysis might be in the analysis of individuals' medical records. In such a case, there might be a need to draw insights from data while at the same time maintaining privacy of the participants. Such cases have given birth to privacy-preserving data analyitics. Privacy is typically guaranteed by a differentially private mechanism. In this paper, we present a novel mechanism for privacy-preserving quantum machine learning. The mechanism is tested on the sensitive dataset that contains features and target labels for breast cancer prediction. The results obtained underline the utility of this mechanism.

AB - The advance of artificial intelligence in general and machine learning in particular has resulted in the need to pay more attention to the provision of privacy to the data being anlyzed. An example of sensitive data analysis might be in the analysis of individuals' medical records. In such a case, there might be a need to draw insights from data while at the same time maintaining privacy of the participants. Such cases have given birth to privacy-preserving data analyitics. Privacy is typically guaranteed by a differentially private mechanism. In this paper, we present a novel mechanism for privacy-preserving quantum machine learning. The mechanism is tested on the sensitive dataset that contains features and target labels for breast cancer prediction. The results obtained underline the utility of this mechanism.

UR - http://www.scopus.com/inward/record.url?scp=85039957233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85039957233&partnerID=8YFLogxK

U2 - 10.1109/AFRCON.2017.8095692

DO - 10.1109/AFRCON.2017.8095692

M3 - Conference contribution

AN - SCOPUS:85039957233

T3 - 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017

SP - 1432

EP - 1435

BT - 2017 IEEE AFRICON

A2 - Cornish, Darryn R.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE AFRICON 2017

Y2 - 18 September 2017 through 20 September 2017

ER -

Senekane M, Mafu M, Taele BM. Privacy-preserving quantum machine learning using differential privacy. In Cornish DR, editor, 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1432-1435. 8095692. (2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017). doi: 10.1109/AFRCON.2017.8095692

Privacy-preserving quantum machine learning using differential privacy

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this