A Systematic Review of Data-Driven Attack Detection Trends in IoT

被引:13
作者
Haque, Safwana [1 ]
El-Moussa, Fadi [2 ]
Komninos, Nikos [1 ]
Muttukrishnan, Rajarajan [1 ]
机构
[1] City Univ London, Sch Sci & Technol, Dept Elect & Elect Engn, Northampton Sq, London EC1V 0HB, England
[2] BT Grp PLC, Ipswich IP5 3RE, England
关键词
IoT; datasets; machine learning; cyberattack; intrusion detection; threat detection; INTRUSION DETECTION; CYBERATTACK DETECTION; BOTNET DETECTION; TON-IOT; INTERNET; SECURITY; THINGS; ARCHITECTURES; SELECTION; ISSUES;
D O I
10.3390/s23167191
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The Internet of Things is perhaps a concept that the world cannot be imagined without today, having become intertwined in our everyday lives in the domestic, corporate and industrial spheres. However, irrespective of the convenience, ease and connectivity provided by the Internet of Things, the security issues and attacks faced by this technological framework are equally alarming and undeniable. In order to address these various security issues, researchers race against evolving technology, trends and attacker expertise. Though much work has been carried out on network security to date, it is still seen to be lagging in the field of Internet of Things networks. This study surveys the latest trends used in security measures for threat detection, primarily focusing on the machine learning and deep learning techniques applied to Internet of Things datasets. It aims to provide an overview of the IoT datasets available today, trends in machine learning and deep learning usage, and the efficiencies of these algorithms on a variety of relevant datasets. The results of this comprehensive survey can serve as a guide and resource for identifying the various datasets, experiments carried out and future research directions in this field.
引用
收藏
页数:29
相关论文
共 139 条
[1]  
Abbasi Fereshteh, 2021, 2021 5th International Conference on Internet of Things and Applications (IoT), DOI 10.1109/IoT52625.2021.9469605
[2]  
Ahemd MM, 2017, 2017 INTERNATIONAL CONFERENCE ON COMMUNICATION TECHNOLOGIES (COMTECH), P104, DOI 10.1109/COMTECH.2017.8065757
[3]   Botnet Detection Approach Using Graph-Based Machine Learning [J].
Alharbi, Afnan ;
Alsubhi, Khalid .
IEEE ACCESS, 2021, 9 (09) :99166-99180
[4]   TON_IoT Telemetry Dataset: A New Generation Dataset of IoT and IIoT for Data-Driven Intrusion Detection Systems [J].
Alsaedi, Abdullah ;
Moustafa, Nour ;
Tari, Zahir ;
Mahmood, Abdun ;
Anwar, Adnan .
IEEE ACCESS, 2020, 8 :165130-165150
[5]  
Alsamiri J, 2019, INT J ADV COMPUT SC, V10, P627
[6]  
Alshohoumi F, 2019, INT J ADV COMPUT SC, V10, P232
[7]  
Amazon, AWS IOT COR DEV GUID
[8]  
Andrea I, 2015, 2015 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATION (ISCC), P180, DOI 10.1109/ISCC.2015.7405513
[9]  
[Anonymous], ECL MOSQ
[10]  
[Anonymous], 1998, DARPA INTR DET EV DA