Applying Big Data Based Deep Learning System to Intrusion Detection
With vast amounts of data being generated daily and the ever increasing interconnectivity of the world’s internet infrastructures, a machine learning based Intrusion Detection Systems (IDS) has become a vital component to protect our economic and national security. Previous shallow learning and deep...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2020-09-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2020.9020003 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573616410066944 |
|---|---|
| author | Wei Zhong Ning Yu Chunyu Ai |
| author_facet | Wei Zhong Ning Yu Chunyu Ai |
| author_sort | Wei Zhong |
| collection | DOAJ |
| description | With vast amounts of data being generated daily and the ever increasing interconnectivity of the world’s internet infrastructures, a machine learning based Intrusion Detection Systems (IDS) has become a vital component to protect our economic and national security. Previous shallow learning and deep learning strategies adopt the single learning model approach for intrusion detection. The single learning model approach may experience problems to understand increasingly complicated data distribution of intrusion patterns. Particularly, the single deep learning model may not be effective to capture unique patterns from intrusive attacks having a small number of samples. In order to further enhance the performance of machine learning based IDS, we propose the Big Data based Hierarchical Deep Learning System (BDHDLS). BDHDLS utilizes behavioral features and content features to understand both network traffic characteristics and information stored in the payload. Each deep learning model in the BDHDLS concentrates its efforts to learn the unique data distribution in one cluster. This strategy can increase the detection rate of intrusive attacks as compared to the previous single learning model approaches. Based on parallel training strategy and big data techniques, the model construction time of BDHDLS is reduced substantially when multiple machines are deployed. |
| format | Article |
| id | doaj-art-4b012cc857124ce69c4d44fb418b72db |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2020-09-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-4b012cc857124ce69c4d44fb418b72db2025-02-02T03:45:08ZengTsinghua University PressBig Data Mining and Analytics2096-06542020-09-013318119510.26599/BDMA.2020.9020003Applying Big Data Based Deep Learning System to Intrusion DetectionWei Zhong0Ning Yu1Chunyu Ai2<institution content-type="dept">Division of Math and Computer Science</institution>, <institution>University of South Carolina Upstate</institution>, <city>Spartanburg</city>, <state>SC</state> <postal-code>29303</postal-code>, <country>USA</country>.<institution content-type="dept">Division of Math and Computer Science</institution>, <institution>University of South Carolina Upstate</institution>, <city>Spartanburg</city>, <state>SC</state> <postal-code>29303</postal-code>, <country>USA</country>.<institution content-type="dept">Division of Math and Computer Science</institution>, <institution>University of South Carolina Upstate</institution>, <city>Spartanburg</city>, <state>SC</state> <postal-code>29303</postal-code>, <country>USA</country>.With vast amounts of data being generated daily and the ever increasing interconnectivity of the world’s internet infrastructures, a machine learning based Intrusion Detection Systems (IDS) has become a vital component to protect our economic and national security. Previous shallow learning and deep learning strategies adopt the single learning model approach for intrusion detection. The single learning model approach may experience problems to understand increasingly complicated data distribution of intrusion patterns. Particularly, the single deep learning model may not be effective to capture unique patterns from intrusive attacks having a small number of samples. In order to further enhance the performance of machine learning based IDS, we propose the Big Data based Hierarchical Deep Learning System (BDHDLS). BDHDLS utilizes behavioral features and content features to understand both network traffic characteristics and information stored in the payload. Each deep learning model in the BDHDLS concentrates its efforts to learn the unique data distribution in one cluster. This strategy can increase the detection rate of intrusive attacks as compared to the previous single learning model approaches. Based on parallel training strategy and big data techniques, the model construction time of BDHDLS is reduced substantially when multiple machines are deployed.https://www.sciopen.com/article/10.26599/BDMA.2020.9020003intrusion detectiondeep learningconvolution neural networkfully connected feedforward neural networkmulti-level clustering algorithm |
| spellingShingle | Wei Zhong Ning Yu Chunyu Ai Applying Big Data Based Deep Learning System to Intrusion Detection Big Data Mining and Analytics intrusion detection deep learning convolution neural network fully connected feedforward neural network multi-level clustering algorithm |
| title | Applying Big Data Based Deep Learning System to Intrusion Detection |
| title_full | Applying Big Data Based Deep Learning System to Intrusion Detection |
| title_fullStr | Applying Big Data Based Deep Learning System to Intrusion Detection |
| title_full_unstemmed | Applying Big Data Based Deep Learning System to Intrusion Detection |
| title_short | Applying Big Data Based Deep Learning System to Intrusion Detection |
| title_sort | applying big data based deep learning system to intrusion detection |
| topic | intrusion detection deep learning convolution neural network fully connected feedforward neural network multi-level clustering algorithm |
| url | https://www.sciopen.com/article/10.26599/BDMA.2020.9020003 |
| work_keys_str_mv | AT weizhong applyingbigdatabaseddeeplearningsystemtointrusiondetection AT ningyu applyingbigdatabaseddeeplearningsystemtointrusiondetection AT chunyuai applyingbigdatabaseddeeplearningsystemtointrusiondetection |