Presentation 2020-03-06
[Technology Exhibit] Machine learning pipeline for analyzing Large-scale traffic
Morikawa Akira, Bo Hu,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, machine learning becomes promising to automatically extract intelligence from network traffic for cybersecurity, especially botnet detection. For detecting different types of components in a botnet such as scanning bots and its command and control servers, many researches have been proposed to preprocess data, generate traffic-based features, and build machine learning-based inference models, respectively. However, when applying multiple detection methods together to dive into details of the whole structure of a botnet, there may be many overlaps in those methods designed for different purposes such as bot and malicious server detection. In this study, we propose and develop a unified machine learning pipeline to enable diversified cybersecurity analysis. Moreover, we develop a graph-based tool to visualize analysis results. The proposed pipeline can aggregate traffic data preprocessing and generate traffic-based statistical features required in different analysis methods to enhance the computational efficiency, and therefore achieve various analysis on botnet. With the graph-based tool, we correlate the detected malicious hosts to clarify the whole picture of botnets.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) cyber security / botnet / machine learning / visualization
Paper # NS2019-212,IN2019-103
Date of Issue 2020-02-27 (NS, IN)

Conference Information
Committee NS / IN
Conference Date 2020/3/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Royal Hotel Okinawa Zanpa-Misaki
Topics (in Japanese) (See Japanese page)
Topics (in English) General
Chair Yoshikatsu Okazaki(NTT) / Takuji Kishida(NTT-AT)
Vice Chair Akihiro Nakao(Univ. of Tokyo) / Kenji Ishida(Hiroshima City Univ.)
Secretary Akihiro Nakao(Osaka Pref Univ.) / Kenji Ishida(NTT)
Assistant Shinya Kawano(NTT)

Paper Information
Registration To Technical Committee on Network Systems / Technical Committee on Information Networks
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Technology Exhibit] Machine learning pipeline for analyzing Large-scale traffic
Sub Title (in English)
Keyword(1) cyber security
Keyword(2) botnet
Keyword(3) machine learning
Keyword(4) visualization
1st Author's Name Morikawa Akira
1st Author's Affiliation NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT)
2nd Author's Name Bo Hu
2nd Author's Affiliation NIPPON TELEGRAPH AND TELEPHONE CORPORATION(NTT)
Date 2020-03-06
Paper # NS2019-212,IN2019-103
Volume (vol) vol.119
Number (no) NS-460,IN-461
Page pp.pp.191-191(NS), pp.151-151(IN),
#Pages 1
Date of Issue 2020-02-27 (NS, IN)