1. NCCU Academic Hub
  2. 學術產出
  3. 商學院
  4. 會議論文
  5. Item

學術產出-會議論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 Network-traffic anomaly detection with incremental majority learning
作者 郁方
Huang, Shin-Ying
Yu, Fang
Tsaih, Rua-Huan
Huang, Yennun
蔡瑞煌
貢獻者 資管系
關鍵詞 Computer crime; Data mining; Mercury (metal); Neural networks; Statistical tests; Adaptive modeling; Changing environment; Data abstraction; Essential features; Incremental learning; Intrusion Detection Systems; Outlier Detection; Training and testing; Intrusion detection
日期 2015
上傳時間 9-八月-2017 17:28:34 (UTC+8)
摘要 Detecting anomaly behavior in large network traffic data has presented a great challenge in designing effective intrusion detection systems. We propose an adaptive model to learn majority patterns under a dynamic changing environment. We first propose unsupervised learning on data abstraction to extract essential features of samples. We then adopt incremental majority learning with iterative evolutions on fitting envelopes to characterize the majority of samples within moving windows. A network traffic sample is considered an anomaly if its abstract feature falls on the outside of the fitting envelope. We justify the effectiveness of the presented approach against 150000+ traffic samples from the NSL-KDD dataset in training and testing, demonstrating positive promise in detecting network attacks by identifying samples that have abnormal features. © 2015 IEEE.
關聯 Proceedings of the International Joint Conference on Neural Networks, 2015-September
資料類型 conference
DOI http://dx.doi.org/10.1109/IJCNN.2015.7280573
dc.contributor 資管系zh_Tw
dc.creator (作者) 郁方zh_TW
dc.creator (作者) Huang, Shin-Yingen_US
dc.creator (作者) Yu, Fangen_US
dc.creator (作者) Tsaih, Rua-Huanen_US
dc.creator (作者) Huang, Yennunen_US
dc.creator (作者) 蔡瑞煌zh_TW
dc.date (日期) 2015en_US
dc.date.accessioned 9-八月-2017 17:28:34 (UTC+8)-
dc.date.available 9-八月-2017 17:28:34 (UTC+8)-
dc.date.issued (上傳時間) 9-八月-2017 17:28:34 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/111697-
dc.description.abstract (摘要) Detecting anomaly behavior in large network traffic data has presented a great challenge in designing effective intrusion detection systems. We propose an adaptive model to learn majority patterns under a dynamic changing environment. We first propose unsupervised learning on data abstraction to extract essential features of samples. We then adopt incremental majority learning with iterative evolutions on fitting envelopes to characterize the majority of samples within moving windows. A network traffic sample is considered an anomaly if its abstract feature falls on the outside of the fitting envelope. We justify the effectiveness of the presented approach against 150000+ traffic samples from the NSL-KDD dataset in training and testing, demonstrating positive promise in detecting network attacks by identifying samples that have abnormal features. © 2015 IEEE.en_US
dc.format.extent 210 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) Proceedings of the International Joint Conference on Neural Networks, 2015-Septemberen_US
dc.subject (關鍵詞) Computer crime; Data mining; Mercury (metal); Neural networks; Statistical tests; Adaptive modeling; Changing environment; Data abstraction; Essential features; Incremental learning; Intrusion Detection Systems; Outlier Detection; Training and testing; Intrusion detectionen_US
dc.title (題名) Network-traffic anomaly detection with incremental majority learningen_US
dc.type (資料類型) conference-
dc.identifier.doi (DOI) 10.1109/IJCNN.2015.7280573-
dc.doi.uri (DOI) http://dx.doi.org/10.1109/IJCNN.2015.7280573-