A network intrusion detection method designed for few-shot scenarios
Existing intrusion detection techniques often require numerous malicious samples for model training.However, in real-world scenarios, only a small number of intrusion traffic samples can be obtained, which belong to few-shot scenarios.To address this challenge, a network intrusion detection method d...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2023-10-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023166/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533630161092608 |
|---|---|
| author | Weichen HU Congyuan XU Yong ZHAN Guanghui CHEN Siqing LIU Zhiqiang WANG Xiaolin WANG |
| author_facet | Weichen HU Congyuan XU Yong ZHAN Guanghui CHEN Siqing LIU Zhiqiang WANG Xiaolin WANG |
| author_sort | Weichen HU |
| collection | DOAJ |
| description | Existing intrusion detection techniques often require numerous malicious samples for model training.However, in real-world scenarios, only a small number of intrusion traffic samples can be obtained, which belong to few-shot scenarios.To address this challenge, a network intrusion detection method designed for few-shot scenarios was proposed.The method comprised two main parts: a packet sampling module and a meta-learning module.The packet sampling module was used for filtering, segmenting, and recombining raw network data, while the meta-learning module was used for feature extraction and result classification.Experimental results based on three few-shot datasets constructed from real network traffic data sources show that the method exhibits good applicability and fast convergence and effectively reduces the occurrence of outliers.In the case of 10 training samples, the maximum achievable detection rate is 99.29%, while the accuracy rate can reach a maximum of 97.93%.These findings demonstrate a noticeable improvement of 0.12% and 0.37% respectively, in comparison to existing algorithms. |
| format | Article |
| id | doaj-art-518f9334ae834429a2210f6e0f48ec8c |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2023-10-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-518f9334ae834429a2210f6e0f48ec8c2025-01-15T02:58:03ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-10-01398510059560149A network intrusion detection method designed for few-shot scenariosWeichen HUCongyuan XUYong ZHANGuanghui CHENSiqing LIUZhiqiang WANGXiaolin WANGExisting intrusion detection techniques often require numerous malicious samples for model training.However, in real-world scenarios, only a small number of intrusion traffic samples can be obtained, which belong to few-shot scenarios.To address this challenge, a network intrusion detection method designed for few-shot scenarios was proposed.The method comprised two main parts: a packet sampling module and a meta-learning module.The packet sampling module was used for filtering, segmenting, and recombining raw network data, while the meta-learning module was used for feature extraction and result classification.Experimental results based on three few-shot datasets constructed from real network traffic data sources show that the method exhibits good applicability and fast convergence and effectively reduces the occurrence of outliers.In the case of 10 training samples, the maximum achievable detection rate is 99.29%, while the accuracy rate can reach a maximum of 97.93%.These findings demonstrate a noticeable improvement of 0.12% and 0.37% respectively, in comparison to existing algorithms.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023166/intrusion detectionfew-shotmeta-learningnetwork securitydeep learning |
| spellingShingle | Weichen HU Congyuan XU Yong ZHAN Guanghui CHEN Siqing LIU Zhiqiang WANG Xiaolin WANG A network intrusion detection method designed for few-shot scenarios Dianxin kexue intrusion detection few-shot meta-learning network security deep learning |
| title | A network intrusion detection method designed for few-shot scenarios |
| title_full | A network intrusion detection method designed for few-shot scenarios |
| title_fullStr | A network intrusion detection method designed for few-shot scenarios |
| title_full_unstemmed | A network intrusion detection method designed for few-shot scenarios |
| title_short | A network intrusion detection method designed for few-shot scenarios |
| title_sort | network intrusion detection method designed for few shot scenarios |
| topic | intrusion detection few-shot meta-learning network security deep learning |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023166/ |
| work_keys_str_mv | AT weichenhu anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT congyuanxu anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT yongzhan anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT guanghuichen anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT siqingliu anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT zhiqiangwang anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT xiaolinwang anetworkintrusiondetectionmethoddesignedforfewshotscenarios AT weichenhu networkintrusiondetectionmethoddesignedforfewshotscenarios AT congyuanxu networkintrusiondetectionmethoddesignedforfewshotscenarios AT yongzhan networkintrusiondetectionmethoddesignedforfewshotscenarios AT guanghuichen networkintrusiondetectionmethoddesignedforfewshotscenarios AT siqingliu networkintrusiondetectionmethoddesignedforfewshotscenarios AT zhiqiangwang networkintrusiondetectionmethoddesignedforfewshotscenarios AT xiaolinwang networkintrusiondetectionmethoddesignedforfewshotscenarios |