A survey of machine learning-based solutions to protect privacy in the Internet of Things

被引：45

作者：

Amiri-Zarandi, Mohammad ^{[1
]}

Dara, Rozita A. ^{[1
]}

Fraser, Evan ^{[2
]}

机构：

[1] Univ Guelph, Sch Comp Sci, Guelph, ON, Canada

[2] Univ Guelph, Dept Geog, Guelph, ON, Canada

来源：

COMPUTERS & SECURITY | 2020年 / 96卷

关键词：

Internet of Things (IoT); Survey; Privacy; Security; ML; Fog/edge computing; DIFFERENTIAL PRIVACY; DATA AGGREGATION; FRAMEWORK; EDGE;

D O I：

10.1016/j.cose.2020.101921

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The Internet of things (IoT) aims to connect everything and everyone around the world to provide diverse applications that improve quality of life. In this technology, the preservation of data privacy plays a crucial role. Recently, many studies have leveraged machine learning (ML) as a strategy to address the privacy issues of IoT including scalability, interoperability, and resource limitation such as computation and energy. In this paper, we aim to review these studies and examine opportunities and concerns related to utilizing data in ML-based solutions for privacy in IoT. We, first, explore and introduce different data sources in IoT and categorize them. Then, we review existing ML-based solutions that are designed and developed to protect privacy in IoT. Finally, we examine the extent to which some data categories have been used with ML-based solutions to preserve privacy and propose other novel opportunities for ML-based solutions to leverage these data sources in the IoT ecosystem. (C) 2020 Elsevier Ltd. All rights reserved.

引用

页数：9

共 90 条

[1] Deep Learning with Differential Privacy [J].

Abadi, Martin ;

Chu, Andy ;

Goodfellow, Ian ;

McMahan, H. Brendan ;

Mironov, Ilya ;

Talwar, Kunal ;

Zhang, Li .

CCS'16: PROCEEDINGS OF THE 2016 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2016, :308-318

[2]

Agarwal R, 2016, 2016 IEEE 3RD WORLD FORUM ON INTERNET OF THINGS (WF-IOT), P70, DOI 10.1109/WF-IoT.2016.7845470

[3]

Al-Qaseemi SA, 2016, PROCEEDINGS OF 2016 FUTURE TECHNOLOGIES CONFERENCE (FTC), P731, DOI 10.1109/FTC.2016.7821686

[4]

[Anonymous], 2017, P PRIV ENH TECHN 201

[5]

[Anonymous], P 2018 55 ACM ESDA I

[6]

[Anonymous], 2016, Proceedings of the 15th International Conference on Information Processing in Sensor Networks

[7]

[Anonymous], 2010, Proceedings of 11th IEEE International Workshop on Signal ProcessingAdvances in Wireless Communications (SPAWC), Marrakech

[8] Scalable and Secure Logistic Regression via Homomorphic Encryption [J].

Aono, Yoshinori ;

Hayashi, Takuya ;

Le Trieu Phong ;

Wang, Lihua .

CODASPY'16: PROCEEDINGS OF THE SIXTH ACM CONFERENCE ON DATA AND APPLICATION SECURITY AND PRIVACY, 2016, :142-144

[9] Privacy-Preserving Logistic Regression with Distributed Data Sources via Homomorphic Encryption [J].

Aono, Yoshinori ;

Hayashi, Takuya ;

Phong, Le Trieu ;

Wang, Lihua .

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2016, E99D (08) :2079-2089

[10]

Audich DhirenA., 2018, IFIP Adv. Inf. Commun. Technol, P29, DOI DOI 10.1007/978-3-319-95276-5_3

← 1 2 3 4 5 6 7 8 9 →