A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method
Network intrusion data are characterized by high feature dimensionality, extreme category imbalance, and complex nonlinear relationships between features and categories. The actual detection accuracy of existing supervised intrusion-detection models performs poorly. To address this problem, this pap...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/4/949 |
| _version_ | 1797621292170477568 |
|---|---|
| author | Jian Luo Yiying Zhang Yannian Wu Yao Xu Xiaoyan Guo Boxiang Shang |
| author_facet | Jian Luo Yiying Zhang Yannian Wu Yao Xu Xiaoyan Guo Boxiang Shang |
| author_sort | Jian Luo |
| collection | DOAJ |
| description | Network intrusion data are characterized by high feature dimensionality, extreme category imbalance, and complex nonlinear relationships between features and categories. The actual detection accuracy of existing supervised intrusion-detection models performs poorly. To address this problem, this paper proposes a multi-channel contrastive learning network-based intrusion-detection method (MCLDM), which combines feature learning in the multi-channel supervised contrastive learning stage and feature extraction in the multi-channel unsupervised contrastive learning stage to train an effective intrusion-detection model. The objective is to research whether feature enrichment and the use of contrastive learning for specific classes of network intrusion data can improve the accuracy of the model. The model is based on an autoencoder to achieve feature reconstruction with supervised contrastive learning and for implementing multi-channel data reconstruction. In the next stage of unsupervised contrastive learning, the extraction of features is implemented using triplet convolutional neural networks (TCNN) to achieve the classification of intrusion data. Through experimental analysis, the multichannel contrastive learning network-based intrusion-detection method achieves 98.43% accuracy in dataset CICIDS17 and 93.94% accuracy in dataset KDDCUP99. |
| first_indexed | 2024-03-11T08:53:47Z |
| format | Article |
| id | doaj.art-5939d48d499244f9adb6f13b84e8cd0c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T08:53:47Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-5939d48d499244f9adb6f13b84e8cd0c2023-11-16T20:12:35ZengMDPI AGElectronics2079-92922023-02-0112494910.3390/electronics12040949A Multi-Channel Contrastive Learning Network Based Intrusion Detection MethodJian Luo0Yiying Zhang1Yannian Wu2Yao Xu3Xiaoyan Guo4Boxiang Shang5Department of Internet of Things Engineering, Tianjin University of Science and Technology, Tianjin 300457, ChinaDepartment of Internet of Things Engineering, Tianjin University of Science and Technology, Tianjin 300457, ChinaShenzhen Guodian Technology Communication Co., Shenzhen 518028, ChinaDepartment of Internet of Things Engineering, Tianjin University of Science and Technology, Tianjin 300457, ChinaInformation and Communication Company, State Grid Tianjin Electric Power Company, Tianjin 300140, ChinaState Grid Tianjin Electric Power Company, Tianjin 300131, ChinaNetwork intrusion data are characterized by high feature dimensionality, extreme category imbalance, and complex nonlinear relationships between features and categories. The actual detection accuracy of existing supervised intrusion-detection models performs poorly. To address this problem, this paper proposes a multi-channel contrastive learning network-based intrusion-detection method (MCLDM), which combines feature learning in the multi-channel supervised contrastive learning stage and feature extraction in the multi-channel unsupervised contrastive learning stage to train an effective intrusion-detection model. The objective is to research whether feature enrichment and the use of contrastive learning for specific classes of network intrusion data can improve the accuracy of the model. The model is based on an autoencoder to achieve feature reconstruction with supervised contrastive learning and for implementing multi-channel data reconstruction. In the next stage of unsupervised contrastive learning, the extraction of features is implemented using triplet convolutional neural networks (TCNN) to achieve the classification of intrusion data. Through experimental analysis, the multichannel contrastive learning network-based intrusion-detection method achieves 98.43% accuracy in dataset CICIDS17 and 93.94% accuracy in dataset KDDCUP99.https://www.mdpi.com/2079-9292/12/4/949network intrusion detectionfeature reconstructionautoencodermulti-channelcontrastive learning |
| spellingShingle | Jian Luo Yiying Zhang Yannian Wu Yao Xu Xiaoyan Guo Boxiang Shang A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method Electronics network intrusion detection feature reconstruction autoencoder multi-channel contrastive learning |
| title | A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method |
| title_full | A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method |
| title_fullStr | A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method |
| title_full_unstemmed | A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method |
| title_short | A Multi-Channel Contrastive Learning Network Based Intrusion Detection Method |
| title_sort | multi channel contrastive learning network based intrusion detection method |
| topic | network intrusion detection feature reconstruction autoencoder multi-channel contrastive learning |
| url | https://www.mdpi.com/2079-9292/12/4/949 |
| work_keys_str_mv | AT jianluo amultichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT yiyingzhang amultichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT yannianwu amultichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT yaoxu amultichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT xiaoyanguo amultichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT boxiangshang amultichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT jianluo multichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT yiyingzhang multichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT yannianwu multichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT yaoxu multichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT xiaoyanguo multichannelcontrastivelearningnetworkbasedintrusiondetectionmethod AT boxiangshang multichannelcontrastivelearningnetworkbasedintrusiondetectionmethod |