Machine Learning for the Internet of Things Security a Systematic Review
Detecting Cybersecurity Attacks in Cyberspace of Things Using Artificial Intelligence Methods: A Systematic Literature Review
ane
Department of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Malaysia
2
Found of Sustainable Energy (ISE), Universiti Tenaga Nasional (UNITEN), Kajang 43000, Malaysia
3
Estimator Scientific discipline Department, Community College, King Saud University, Riyadh 145111, Saudi Arabia
4
Department of Electrical & Computer Engineering, Western Academy, London, ON N6A5B9, Canada
*
Authors to whom correspondence should be addressed.
Academic Editor: Qusay H. Mahmoud
Received: 29 October 2021 / Revised: xxx November 2021 / Accepted: 4 December 2021 / Published: 10 January 2022
Abstract
In recent years, technology has advanced to the 4th industrial revolution (Manufacture four.0), where the Internet of things (IoTs), fog calculating, computer security, and cyberattacks have evolved exponentially on a large calibration. The rapid development of IoT devices and networks in various forms generate enormous amounts of data which in plow demand careful hallmark and security. Artificial intelligence (AI) is considered i of the well-nigh promising methods for addressing cybersecurity threats and providing security. In this study, nosotros nowadays a systematic literature review (SLR) that categorize, map and survey the existing literature on AI methods used to detect cybersecurity attacks in the IoT environment. The scope of this SLR includes an in-depth investigation on nearly AI trending techniques in cybersecurity and state-of-art solutions. A systematic search was performed on various electronic databases (SCOPUS, Scientific discipline Direct, IEEE Xplore, Web of Scientific discipline, ACM, and MDPI). Out of the identified records, eighty studies published between 2016 and 2021 were selected, surveyed and carefully assessed. This review has explored deep learning (DL) and machine learning (ML) techniques used in IoT security, and their effectiveness in detecting attacks. However, several studies have proposed smart intrusion detection systems (IDS) with intelligent architectural frameworks using AI to overcome the existing security and privacy challenges. It is found that support vector machines (SVM) and random woods (RF) are among the most used methods, due to high accuracy detection another reason may exist efficient memory. In add-on, other methods also provide better performance such equally extreme gradient boosting (XGBoost), neural networks (NN) and recurrent neural networks (RNN). This analysis too provides an insight into the AI roadmap to detect threats based on attack categories. Finally, nosotros present recommendations for potential future investigations. View Full-Text
► ▼ Testify Figures
This is an open access article distributed under the Artistic Eatables Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original piece of work is properly cited
Share and Cite
MDPI and ACS Fashion
Abdullahi, M.; Baashar, Y.; Alhussian, H.; Alwadain, A.; Aziz, N.; Capretz, 50.F.; Abdulkadir, S.J. Detecting Cybersecurity Attacks in Internet of Things Using Artificial Intelligence Methods: A Systematic Literature Review. Electronics 2022, xi, 198. https://doi.org/10.3390/electronics11020198
AMA Manner
Abdullahi Chiliad, Baashar Y, Alhussian H, Alwadain A, Aziz Northward, Capretz LF, Abdulkadir SJ. Detecting Cybersecurity Attacks in Net of Things Using Artificial Intelligence Methods: A Systematic Literature Review. Electronics. 2022; xi(2):198. https://doi.org/10.3390/electronics11020198
Chicago/Turabian Style
Abdullahi, Mujaheed, Yahia Baashar, Hitham Alhussian, Ayed Alwadain, Norshakirah Aziz, Luiz F. Capretz, and Said J. Abdulkadir. 2022. "Detecting Cybersecurity Attacks in Internet of Things Using Artificial Intelligence Methods: A Systematic Literature Review" Electronics 11, no. 2: 198. https://doi.org/10.3390/electronics11020198
Note that from the first outcome of 2016, MDPI journals use article numbers instead of page numbers. Meet further details here.
Article Metrics
Commodity Access Statistics
For more than information on the journal statistics, click hither.
Multiple requests from the same IP accost are counted every bit one view.
Source: https://www.mdpi.com/2079-9292/11/2/198
0 Response to "Machine Learning for the Internet of Things Security a Systematic Review"
Postar um comentário