Semi-supervised tri-Adaboost algorithm for network intrusion detection
Network intrusion detection is a relatively mature research topic, but one that remains challenging particular as technologies and threat landscape evolve. Here, a semi-supervised tri-Adaboost (STA) algorithm is proposed. In the algorithm, three different Adaboost algorithms are used as the weak cla...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2019-06-01
|
| Series: | International Journal of Distributed Sensor Networks |
| Online Access: | https://doi.org/10.1177/1550147719846052 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553116681109504 |
|---|---|
| author | Yali Yuan Liuwei Huo Yachao Yuan Zhixiao Wang |
| author_facet | Yali Yuan Liuwei Huo Yachao Yuan Zhixiao Wang |
| author_sort | Yali Yuan |
| collection | DOAJ |
| description | Network intrusion detection is a relatively mature research topic, but one that remains challenging particular as technologies and threat landscape evolve. Here, a semi-supervised tri-Adaboost (STA) algorithm is proposed. In the algorithm, three different Adaboost algorithms are used as the weak classifiers (both for continuous and categorical data), constituting the decision stumps in the tri-training method. In addition, the chi-square method is used to reduce the dimension of feature and improve computational efficiency. We then conduct extensive numerical studies using different training and testing samples in the KDDcup99 dataset and discover the flows demonstrated that (1) high accuracy can be obtained using a training dataset which consists of a small number of labeled and a large number of unlabeled samples. (2) The algorithm proposed is reproducible and consistent over different runs. (3) The proposed algorithm outperforms other existing learning algorithms, even with only a small amount of labeled data in the training phase. (4) The proposed algorithm has a short execution time and a low false positive rate, while providing a desirable detection rate. |
| format | Article |
| id | doaj-art-4abc3395c37945bf8ab3986b745b9875 |
| institution | Kabale University |
| issn | 1550-1477 |
| language | English |
| publishDate | 2019-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Distributed Sensor Networks |
| spelling | doaj-art-4abc3395c37945bf8ab3986b745b98752025-02-03T05:55:24ZengWileyInternational Journal of Distributed Sensor Networks1550-14772019-06-011510.1177/1550147719846052Semi-supervised tri-Adaboost algorithm for network intrusion detectionYali Yuan0Liuwei Huo1Yachao Yuan2Zhixiao Wang3Telematics Group, Institute of Computer Science, University of Göttingen, Göttingen, GermanySchool of Computer Science and Engineering, Northeastern University, Shenyang, ChinaSmart Mobility Research Group, Chair of Information Management, Faculty of Economic Sciences, University of Göttingen, Göttingen, GermanySchool of Electronic and Information Engineering, Xi’an Jiaotong University, Xi’an, ChinaNetwork intrusion detection is a relatively mature research topic, but one that remains challenging particular as technologies and threat landscape evolve. Here, a semi-supervised tri-Adaboost (STA) algorithm is proposed. In the algorithm, three different Adaboost algorithms are used as the weak classifiers (both for continuous and categorical data), constituting the decision stumps in the tri-training method. In addition, the chi-square method is used to reduce the dimension of feature and improve computational efficiency. We then conduct extensive numerical studies using different training and testing samples in the KDDcup99 dataset and discover the flows demonstrated that (1) high accuracy can be obtained using a training dataset which consists of a small number of labeled and a large number of unlabeled samples. (2) The algorithm proposed is reproducible and consistent over different runs. (3) The proposed algorithm outperforms other existing learning algorithms, even with only a small amount of labeled data in the training phase. (4) The proposed algorithm has a short execution time and a low false positive rate, while providing a desirable detection rate.https://doi.org/10.1177/1550147719846052 |
| spellingShingle | Yali Yuan Liuwei Huo Yachao Yuan Zhixiao Wang Semi-supervised tri-Adaboost algorithm for network intrusion detection International Journal of Distributed Sensor Networks |
| title | Semi-supervised tri-Adaboost algorithm for network intrusion detection |
| title_full | Semi-supervised tri-Adaboost algorithm for network intrusion detection |
| title_fullStr | Semi-supervised tri-Adaboost algorithm for network intrusion detection |
| title_full_unstemmed | Semi-supervised tri-Adaboost algorithm for network intrusion detection |
| title_short | Semi-supervised tri-Adaboost algorithm for network intrusion detection |
| title_sort | semi supervised tri adaboost algorithm for network intrusion detection |
| url | https://doi.org/10.1177/1550147719846052 |
| work_keys_str_mv | AT yaliyuan semisupervisedtriadaboostalgorithmfornetworkintrusiondetection AT liuweihuo semisupervisedtriadaboostalgorithmfornetworkintrusiondetection AT yachaoyuan semisupervisedtriadaboostalgorithmfornetworkintrusiondetection AT zhixiaowang semisupervisedtriadaboostalgorithmfornetworkintrusiondetection |