Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble
In order to adapt to the rapid development of network technology and network security detection in different scenarios, the generalization ability of the classifier needs to be further improved and has the ability to detect unknown attacks. However, the generalization ability of a single classifier...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/13/10/1814 |
| _version_ | 1797513109338849280 |
|---|---|
| author | Aili Wang Wenya Wang Huaming Zhou Jian Zhang |
| author_facet | Aili Wang Wenya Wang Huaming Zhou Jian Zhang |
| author_sort | Aili Wang |
| collection | DOAJ |
| description | In order to adapt to the rapid development of network technology and network security detection in different scenarios, the generalization ability of the classifier needs to be further improved and has the ability to detect unknown attacks. However, the generalization ability of a single classifier is limited to dealing with class imbalance, and the previous ensemble methods inevitably increase the training cost. Therefore, in this paper, a novel network intrusion detection algorithm combined with group convolution is proposed to improve the generalization performance of the model. The basic classifier uses group convolution with symmetric structure instead of ordinary convolution neural network, which is trained by the cyclic cosine annealing learning rate. Through snapshot ensemble, the generalization ability of the integration model is improved without increasing the training cost. The effectiveness of this method is proved on NSL-KDD and UNSW-NB15 datasets compared to six other ensemble methods, the classification accuracy can achieve 85.82% and 80.38%, respectively. |
| first_indexed | 2024-03-10T06:10:05Z |
| format | Article |
| id | doaj.art-086b52309608458f81dae6d2436b4413 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T06:10:05Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-086b52309608458f81dae6d2436b44132023-11-22T20:09:30ZengMDPI AGSymmetry2073-89942021-09-011310181410.3390/sym13101814Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot EnsembleAili Wang0Wenya Wang1Huaming Zhou2Jian Zhang3Heilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application, College of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaHeilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application, College of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaHeilongjiang Province Key Laboratory of Laser Spectroscopy Technology and Application, College of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, ChinaCollege of Artificial Intelligence, Wuxi Vocational College of Science and Technology, Wuxi 214028, ChinaIn order to adapt to the rapid development of network technology and network security detection in different scenarios, the generalization ability of the classifier needs to be further improved and has the ability to detect unknown attacks. However, the generalization ability of a single classifier is limited to dealing with class imbalance, and the previous ensemble methods inevitably increase the training cost. Therefore, in this paper, a novel network intrusion detection algorithm combined with group convolution is proposed to improve the generalization performance of the model. The basic classifier uses group convolution with symmetric structure instead of ordinary convolution neural network, which is trained by the cyclic cosine annealing learning rate. Through snapshot ensemble, the generalization ability of the integration model is improved without increasing the training cost. The effectiveness of this method is proved on NSL-KDD and UNSW-NB15 datasets compared to six other ensemble methods, the classification accuracy can achieve 85.82% and 80.38%, respectively.https://www.mdpi.com/2073-8994/13/10/1814intrusion detectionclass imbalanceconvolution neural networkgroup convolutionsnapshot ensemble |
| spellingShingle | Aili Wang Wenya Wang Huaming Zhou Jian Zhang Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble Symmetry intrusion detection class imbalance convolution neural network group convolution snapshot ensemble |
| title | Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble |
| title_full | Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble |
| title_fullStr | Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble |
| title_full_unstemmed | Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble |
| title_short | Network Intrusion Detection Algorithm Combined with Group Convolution Network and Snapshot Ensemble |
| title_sort | network intrusion detection algorithm combined with group convolution network and snapshot ensemble |
| topic | intrusion detection class imbalance convolution neural network group convolution snapshot ensemble |
| url | https://www.mdpi.com/2073-8994/13/10/1814 |
| work_keys_str_mv | AT ailiwang networkintrusiondetectionalgorithmcombinedwithgroupconvolutionnetworkandsnapshotensemble AT wenyawang networkintrusiondetectionalgorithmcombinedwithgroupconvolutionnetworkandsnapshotensemble AT huamingzhou networkintrusiondetectionalgorithmcombinedwithgroupconvolutionnetworkandsnapshotensemble AT jianzhang networkintrusiondetectionalgorithmcombinedwithgroupconvolutionnetworkandsnapshotensemble |