Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks
Abstract Network traffic must be monitored and analyzed for any abnormal activity in order to detect intrusions and to notify administrators of any attacks. A novel ensemble of deep learning technique is proposed to enhance the efficiency of Packet Flow Classification in Network Intrusion Detection...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-88243-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862459652374528 |
|---|---|
| author | Selvakumar B Sivaanandh M Muneeswaran K Lakshmanan B |
| author_facet | Selvakumar B Sivaanandh M Muneeswaran K Lakshmanan B |
| author_sort | Selvakumar B |
| collection | DOAJ |
| description | Abstract Network traffic must be monitored and analyzed for any abnormal activity in order to detect intrusions and to notify administrators of any attacks. A novel ensemble of deep learning technique is proposed to enhance the efficiency of Packet Flow Classification in Network Intrusion Detection System (NIDS). The proposed work consists of three phases: (i) Feature Augmented Convolutional Neural Network (FA-CNN) (ii) Deep Autoencoder (iii) Ensemble of FA-CNN and Deep Autoencoder. In FA-CNN, CNN is trained with augmented features selected using Mutual Information. The FA-CNN is ensembled with Deep Autoencoder to design the ensemble of the classifier. To assess the stated ensemble model, numerous experiments are conducted on benchmark datasets like NSL-KDD and CICDS2017. The result findings are compared with the recent methodologies to assess the performance of the stated work. The results indicate that the suggested work performs better than the existing works with the overall accuracy of 97% for NSLKDD and 95% for CICIDS2017 dataset. Also, the proposed method improved the detection rate of minority attack classes like U2R in NSLKDD and Hearbleed in CICIDS2017. |
| format | Article |
| id | doaj-art-1af977db8abc411299594adfd88867db |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1af977db8abc411299594adfd88867db2025-02-09T12:31:19ZengNature PortfolioScientific Reports2045-23222025-02-0115111710.1038/s41598-025-88243-6Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacksSelvakumar B0Sivaanandh M1Muneeswaran K2Lakshmanan B3Department of Computer Science and Engineering, Mepco Schlenk Engineering CollegeDepartment of Computer Science and Engineering, Mepco Schlenk Engineering CollegeDepartment of Computer Science and Engineering, Mepco Schlenk Engineering CollegeDepartment of Computer Science and Engineering, Mepco Schlenk Engineering CollegeAbstract Network traffic must be monitored and analyzed for any abnormal activity in order to detect intrusions and to notify administrators of any attacks. A novel ensemble of deep learning technique is proposed to enhance the efficiency of Packet Flow Classification in Network Intrusion Detection System (NIDS). The proposed work consists of three phases: (i) Feature Augmented Convolutional Neural Network (FA-CNN) (ii) Deep Autoencoder (iii) Ensemble of FA-CNN and Deep Autoencoder. In FA-CNN, CNN is trained with augmented features selected using Mutual Information. The FA-CNN is ensembled with Deep Autoencoder to design the ensemble of the classifier. To assess the stated ensemble model, numerous experiments are conducted on benchmark datasets like NSL-KDD and CICDS2017. The result findings are compared with the recent methodologies to assess the performance of the stated work. The results indicate that the suggested work performs better than the existing works with the overall accuracy of 97% for NSLKDD and 95% for CICIDS2017 dataset. Also, the proposed method improved the detection rate of minority attack classes like U2R in NSLKDD and Hearbleed in CICIDS2017.https://doi.org/10.1038/s41598-025-88243-6 |
| spellingShingle | Selvakumar B Sivaanandh M Muneeswaran K Lakshmanan B Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks Scientific Reports |
| title | Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks |
| title_full | Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks |
| title_fullStr | Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks |
| title_full_unstemmed | Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks |
| title_short | Ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks |
| title_sort | ensemble of feature augmented convolutional neural network and deep autoencoder for efficient detection of network attacks |
| url | https://doi.org/10.1038/s41598-025-88243-6 |
| work_keys_str_mv | AT selvakumarb ensembleoffeatureaugmentedconvolutionalneuralnetworkanddeepautoencoderforefficientdetectionofnetworkattacks AT sivaanandhm ensembleoffeatureaugmentedconvolutionalneuralnetworkanddeepautoencoderforefficientdetectionofnetworkattacks AT muneeswarank ensembleoffeatureaugmentedconvolutionalneuralnetworkanddeepautoencoderforefficientdetectionofnetworkattacks AT lakshmananb ensembleoffeatureaugmentedconvolutionalneuralnetworkanddeepautoencoderforefficientdetectionofnetworkattacks |