Securing Machine Learning in the Cloud: A Systematic Review of Cloud Machine Learning Security.

Machine Learning as a Service attacks cloud machine learning security cloud-hosted machine learning models defenses machine learning security systematic review

Journal

Frontiers in big data
ISSN: 2624-909X
Titre abrégé: Front Big Data
Pays: Switzerland
ID NLM: 101770603

Informations de publication

Date de publication:
2020
Historique:
received: 24 07 2020
accepted: 08 10 2020
entrez: 11 3 2021
pubmed: 12 3 2021
medline: 12 3 2021
Statut: epublish

Résumé

With the advances in machine learning (ML) and deep learning (DL) techniques, and the potency of cloud computing in offering services efficiently and cost-effectively, Machine Learning as a Service (MLaaS) cloud platforms have become popular. In addition, there is increasing adoption of third-party cloud services for outsourcing training of DL models, which requires substantial costly computational resources (e.g., high-performance graphics processing units (GPUs)). Such widespread usage of cloud-hosted ML/DL services opens a wide range of attack surfaces for adversaries to exploit the ML/DL system to achieve malicious goals. In this article, we conduct a systematic evaluation of literature of cloud-hosted ML/DL models along both the important dimensions-

Identifiants

pubmed: 33693420
doi: 10.3389/fdata.2020.587139
pii: 587139
pmc: PMC7931962
doi:

Types de publication

Journal Article Review

Langues

eng

Pagination

587139

Informations de copyright

Copyright © 2020 Qayyum, Ijaz, Usama, Iqbal, Qadir, Elkhatib and Al-Fuqaha.

Déclaration de conflit d'intérêts

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Références

IEEE/ACM Trans Comput Biol Bioinform. 2019 Jan-Feb;16(1):113-123
pubmed: 29994005
IEEE Trans Neural Netw Learn Syst. 2019 Sep;30(9):2805-2824
pubmed: 30640631
IEEE Rev Biomed Eng. 2021;14:156-180
pubmed: 32746371

Auteurs

Adnan Qayyum (A)

Information Technology University (ITU), Lahore, Pakistan.

Aneeqa Ijaz (A)

AI4Networks Research Center, University of Oklahoma, Norman, OK, United States.

Muhammad Usama (M)

Information Technology University (ITU), Lahore, Pakistan.

Waleed Iqbal (W)

Social Data Science (SDS) Lab, Queen Mary University of London, London, United Kingdom.

Junaid Qadir (J)

Information Technology University (ITU), Lahore, Pakistan.

Yehia Elkhatib (Y)

School of Computing and Communications, Lancaster University, Lancaster, United Kingdom.

Ala Al-Fuqaha (A)

Hamad Bin Khalifa University (HBKU), Doha, Qatar.

Classifications MeSH