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
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
587139Informations 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