An approach to reduce data dimension in building effective Network Intrusion Detection Systems
The main function of the network Intrusion Detection System (IDS) is to protect the system, analyze andpredict network access behavior of users. These behaviors are considered normal or an attack. Machinelearning methods (ML) are used in IDSs because of the ability to learn from past attack patterns...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
European Alliance for Innovation (EAI)
2019-08-01
|
| Series: | EAI Endorsed Transactions on Context-aware Systems and Applications |
| Subjects: | |
| Online Access: | https://eudl.eu/pdf/10.4108/eai.13-7-2018.162633 |
| _version_ | 1811339999152439296 |
|---|---|
| author | Hoang Thanh Tran Lang |
| author_facet | Hoang Thanh Tran Lang |
| author_sort | Hoang Thanh |
| collection | DOAJ |
| description | The main function of the network Intrusion Detection System (IDS) is to protect the system, analyze andpredict network access behavior of users. These behaviors are considered normal or an attack. Machinelearning methods (ML) are used in IDSs because of the ability to learn from past attack patterns to recognizenew attack patterns. These methods are effective but have relatively high computational costs. Meanwhile,the traffic of network data is growing rapidly, the computational cost issues need to be addressed. This paper addresses the use of algorithms combined with information metrics to reduce the features of the dataset to be analyzed. As the result, it helps to build IDSs with lower cost but higher performance suitable for large scale networks. The test results on the UNSW-NB15 dataset demonstrate: with the optimal set of features suitable for the attack type as well as the machine learning method, the quality of classification is improved with less training and testing time. |
| first_indexed | 2024-04-13T18:35:52Z |
| format | Article |
| id | doaj.art-0f2efa47c4c7469293da73c8c9dad819 |
| institution | Directory Open Access Journal |
| issn | 2409-0026 |
| language | English |
| last_indexed | 2024-04-13T18:35:52Z |
| publishDate | 2019-08-01 |
| publisher | European Alliance for Innovation (EAI) |
| record_format | Article |
| series | EAI Endorsed Transactions on Context-aware Systems and Applications |
| spelling | doaj.art-0f2efa47c4c7469293da73c8c9dad8192022-12-22T02:34:53ZengEuropean Alliance for Innovation (EAI)EAI Endorsed Transactions on Context-aware Systems and Applications2409-00262019-08-0161810.4108/eai.13-7-2018.162633An approach to reduce data dimension in building effective Network Intrusion Detection SystemsHoang Thanh0Tran Lang1Lac Hong University, VietnamInstitute of Applied Mechanics and Informatics, VAST, VietnamThe main function of the network Intrusion Detection System (IDS) is to protect the system, analyze andpredict network access behavior of users. These behaviors are considered normal or an attack. Machinelearning methods (ML) are used in IDSs because of the ability to learn from past attack patterns to recognizenew attack patterns. These methods are effective but have relatively high computational costs. Meanwhile,the traffic of network data is growing rapidly, the computational cost issues need to be addressed. This paper addresses the use of algorithms combined with information metrics to reduce the features of the dataset to be analyzed. As the result, it helps to build IDSs with lower cost but higher performance suitable for large scale networks. The test results on the UNSW-NB15 dataset demonstrate: with the optimal set of features suitable for the attack type as well as the machine learning method, the quality of classification is improved with less training and testing time.https://eudl.eu/pdf/10.4108/eai.13-7-2018.162633intrusion detection systemmachine learningfeature selectionunsw-nb15 dataset |
| spellingShingle | Hoang Thanh Tran Lang An approach to reduce data dimension in building effective Network Intrusion Detection Systems EAI Endorsed Transactions on Context-aware Systems and Applications intrusion detection system machine learning feature selection unsw-nb15 dataset |
| title | An approach to reduce data dimension in building effective Network Intrusion Detection Systems |
| title_full | An approach to reduce data dimension in building effective Network Intrusion Detection Systems |
| title_fullStr | An approach to reduce data dimension in building effective Network Intrusion Detection Systems |
| title_full_unstemmed | An approach to reduce data dimension in building effective Network Intrusion Detection Systems |
| title_short | An approach to reduce data dimension in building effective Network Intrusion Detection Systems |
| title_sort | approach to reduce data dimension in building effective network intrusion detection systems |
| topic | intrusion detection system machine learning feature selection unsw-nb15 dataset |
| url | https://eudl.eu/pdf/10.4108/eai.13-7-2018.162633 |
| work_keys_str_mv | AT hoangthanh anapproachtoreducedatadimensioninbuildingeffectivenetworkintrusiondetectionsystems AT tranlang anapproachtoreducedatadimensioninbuildingeffectivenetworkintrusiondetectionsystems AT hoangthanh approachtoreducedatadimensioninbuildingeffectivenetworkintrusiondetectionsystems AT tranlang approachtoreducedatadimensioninbuildingeffectivenetworkintrusiondetectionsystems |