An intrusion detection system for the internet of things based on machine learning: review and challenges
An intrusion detection system (IDS) is an active research topic and is regarded as one of the important applications of machine learning. An IDS is a classifier that predicts the class of input records associated with certain types of attacks. In this article, we present a review of IDSs from the pe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Published: |
Multidisciplinary Digital Publishing Institute
2021
|
| _version_ | 1796983155258818560 |
|---|---|
| author | Adnan, Ahmed Muhammed, Abdullah Abd Ghani, Abdul Azim Abdullah, Azizol Hakim, Fahrul |
| author_facet | Adnan, Ahmed Muhammed, Abdullah Abd Ghani, Abdul Azim Abdullah, Azizol Hakim, Fahrul |
| author_sort | Adnan, Ahmed |
| collection | UPM |
| description | An intrusion detection system (IDS) is an active research topic and is regarded as one of the important applications of machine learning. An IDS is a classifier that predicts the class of input records associated with certain types of attacks. In this article, we present a review of IDSs from the perspective of machine learning. We present the three main challenges of an IDS, in general, and of an IDS for the Internet of Things (IoT), in particular, namely concept drift, high dimensionality, and computational complexity. Studies on solving each challenge and the direction of ongoing research are addressed. In addition, in this paper, we dedicate a separate section for presenting datasets of an IDS. In particular, three main datasets, namely KDD99, NSL, and Kyoto, are presented. This article concludes that three elements of concept drift, high-dimensional awareness, and computational awareness that are symmetric in their effect and need to be addressed in the neural network (NN)-based model for an IDS in the IoT. |
| first_indexed | 2024-03-06T11:02:25Z |
| format | Article |
| id | upm.eprints-95865 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-03-06T11:02:25Z |
| publishDate | 2021 |
| publisher | Multidisciplinary Digital Publishing Institute |
| record_format | dspace |
| spelling | upm.eprints-958652023-03-30T04:13:11Z http://psasir.upm.edu.my/id/eprint/95865/ An intrusion detection system for the internet of things based on machine learning: review and challenges Adnan, Ahmed Muhammed, Abdullah Abd Ghani, Abdul Azim Abdullah, Azizol Hakim, Fahrul An intrusion detection system (IDS) is an active research topic and is regarded as one of the important applications of machine learning. An IDS is a classifier that predicts the class of input records associated with certain types of attacks. In this article, we present a review of IDSs from the perspective of machine learning. We present the three main challenges of an IDS, in general, and of an IDS for the Internet of Things (IoT), in particular, namely concept drift, high dimensionality, and computational complexity. Studies on solving each challenge and the direction of ongoing research are addressed. In addition, in this paper, we dedicate a separate section for presenting datasets of an IDS. In particular, three main datasets, namely KDD99, NSL, and Kyoto, are presented. This article concludes that three elements of concept drift, high-dimensional awareness, and computational awareness that are symmetric in their effect and need to be addressed in the neural network (NN)-based model for an IDS in the IoT. Multidisciplinary Digital Publishing Institute 2021 Article PeerReviewed Adnan, Ahmed and Muhammed, Abdullah and Abd Ghani, Abdul Azim and Abdullah, Azizol and Hakim, Fahrul (2021) An intrusion detection system for the internet of things based on machine learning: review and challenges. Symmetry-Basel, 13 (6). art. no. 1011. pp. 1-13. ISSN 2073-8994 https://www.mdpi.com/2073-8994/13/6/1011 10.3390/sym13061011 |
| spellingShingle | Adnan, Ahmed Muhammed, Abdullah Abd Ghani, Abdul Azim Abdullah, Azizol Hakim, Fahrul An intrusion detection system for the internet of things based on machine learning: review and challenges |
| title | An intrusion detection system for the internet of things based on machine learning: review and challenges |
| title_full | An intrusion detection system for the internet of things based on machine learning: review and challenges |
| title_fullStr | An intrusion detection system for the internet of things based on machine learning: review and challenges |
| title_full_unstemmed | An intrusion detection system for the internet of things based on machine learning: review and challenges |
| title_short | An intrusion detection system for the internet of things based on machine learning: review and challenges |
| title_sort | intrusion detection system for the internet of things based on machine learning review and challenges |
| work_keys_str_mv | AT adnanahmed anintrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT muhammedabdullah anintrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT abdghaniabdulazim anintrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT abdullahazizol anintrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT hakimfahrul anintrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT adnanahmed intrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT muhammedabdullah intrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT abdghaniabdulazim intrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT abdullahazizol intrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges AT hakimfahrul intrusiondetectionsystemfortheinternetofthingsbasedonmachinelearningreviewandchallenges |