ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets
Network intrusion detection models are vital techniques for ensuring cybersecurity. However, existing models face several challenges, such as insufficient feature extraction capabilities, dataset imbalance, and suboptimal detection accuracy. In this paper, a new type of model (ResIncepNet-SA) based...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/2/956 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589214736187392 |
|---|---|
| author | Guorui Liu Tianlin Zhang Hualin Dai Xinyang Cheng Daoxuan Yang |
| author_facet | Guorui Liu Tianlin Zhang Hualin Dai Xinyang Cheng Daoxuan Yang |
| author_sort | Guorui Liu |
| collection | DOAJ |
| description | Network intrusion detection models are vital techniques for ensuring cybersecurity. However, existing models face several challenges, such as insufficient feature extraction capabilities, dataset imbalance, and suboptimal detection accuracy. In this paper, a new type of model (ResIncepNet-SA) based on InceptionNet, Resnet, and convolutional neural networks with a self-attention mechanism was proposed to detect network intrusions. The model used the PCA-ADASYN algorithm to compress network traffic features, extract high-correlation feature datasets, and oversample and balance the feature datasets to classify abnormal network traffic. The experimental results show that the accuracy, precision, recall, and F1-score of the proposed ResIncepNet-SA model using the NSL-KDD dataset reach 0.99366, 0.99343, 0.99339, and 0.99338, respectively. This model enhances the accuracy of abnormal network traffic detection and outperforms existing models when applied to imbalanced datasets, offering a new solution for network traffic intrusion detection. |
| format | Article |
| id | doaj-art-ba1ed744cb3a4f11b07854587e43cf90 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-ba1ed744cb3a4f11b07854587e43cf902025-01-24T13:21:29ZengMDPI AGApplied Sciences2076-34172025-01-0115295610.3390/app15020956ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced DatasetsGuorui Liu0Tianlin Zhang1Hualin Dai2Xinyang Cheng3Daoxuan Yang4School of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, ChinaSchool of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, ChinaSchool of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, ChinaSchool of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, ChinaSchool of Computer and Information Engineering, Tianjin Chengjian University, Tianjin 300384, ChinaNetwork intrusion detection models are vital techniques for ensuring cybersecurity. However, existing models face several challenges, such as insufficient feature extraction capabilities, dataset imbalance, and suboptimal detection accuracy. In this paper, a new type of model (ResIncepNet-SA) based on InceptionNet, Resnet, and convolutional neural networks with a self-attention mechanism was proposed to detect network intrusions. The model used the PCA-ADASYN algorithm to compress network traffic features, extract high-correlation feature datasets, and oversample and balance the feature datasets to classify abnormal network traffic. The experimental results show that the accuracy, precision, recall, and F1-score of the proposed ResIncepNet-SA model using the NSL-KDD dataset reach 0.99366, 0.99343, 0.99339, and 0.99338, respectively. This model enhances the accuracy of abnormal network traffic detection and outperforms existing models when applied to imbalanced datasets, offering a new solution for network traffic intrusion detection.https://www.mdpi.com/2076-3417/15/2/956network intrusion detectionfeature extractionunbalanced datasetCNN |
| spellingShingle | Guorui Liu Tianlin Zhang Hualin Dai Xinyang Cheng Daoxuan Yang ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets Applied Sciences network intrusion detection feature extraction unbalanced dataset CNN |
| title | ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets |
| title_full | ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets |
| title_fullStr | ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets |
| title_full_unstemmed | ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets |
| title_short | ResInceptNet-SA: A Network Traffic Intrusion Detection Model Fusing Feature Selection and Balanced Datasets |
| title_sort | resinceptnet sa a network traffic intrusion detection model fusing feature selection and balanced datasets |
| topic | network intrusion detection feature extraction unbalanced dataset CNN |
| url | https://www.mdpi.com/2076-3417/15/2/956 |
| work_keys_str_mv | AT guoruiliu resinceptnetsaanetworktrafficintrusiondetectionmodelfusingfeatureselectionandbalanceddatasets AT tianlinzhang resinceptnetsaanetworktrafficintrusiondetectionmodelfusingfeatureselectionandbalanceddatasets AT hualindai resinceptnetsaanetworktrafficintrusiondetectionmodelfusingfeatureselectionandbalanceddatasets AT xinyangcheng resinceptnetsaanetworktrafficintrusiondetectionmodelfusingfeatureselectionandbalanceddatasets AT daoxuanyang resinceptnetsaanetworktrafficintrusiondetectionmodelfusingfeatureselectionandbalanceddatasets |